© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107942
    Prev
    Next
    INDEX
    Explanations

    regenerative and degenerate

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects terms related to regeneration and degeneration in medical and scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron detects occurrences of the root “generat” (e.g. generate, generation, regeneration, regenerative, degenerative) in words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ejerc
    -0.84
    Ἴ
    -0.79
    wasn
    -0.79
    っており
    -0.79
    カテ
    -0.77
    сина
    -0.75
    Aler
    -0.75
    ина
    -0.75
    Visite
    -0.75
     STANFORD
    -0.74
    POSITIVE LOGITS
    regener
    1.07
     Regener
    0.98
     braking
    0.95
     regenerative
    0.93
     Regent
    0.92
     regenerate
    0.84
     regener
    0.82
     Regen
    0.81
    ative
    0.81
    cija
    0.80
    Activations Density 0.020%

    No Known Activations