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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 367
    Prev
    Next
    INDEX
    Explanations

    code links URLs

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

    The neuron chiefly detects numeric tokens (i.e. sequences of digits).

    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
     several
    -1.02
     Substanz
    -0.98
     various
    -0.95
     even
    -0.94
     through
    -0.89
     some
    -0.88
     in
    -0.87
     although
    -0.87
     three
    -0.86
    rección
    -0.86
    POSITIVE LOGITS
    で
    0.99
     slums
    0.92
    から
    0.91
     interessant
    0.91
     delightful
    0.89
     Eliminate
    0.88
    Plata
    0.88
     essa
    0.88
     arrogant
    0.87
    pilih
    0.87
    Activations Density 0.002%

    No Known Activations