© 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. 22-GEMMASCOPE-RES-131K
    7. 34039
    Prev
    Next
    INDEX
    Explanations

    statement or code endings

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

    The neuron fires on numeric constants (especially hexadecimal or other literal numbers) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     need
    -0.91
     estrutura
    -0.90
     APPARATUS
    -0.89
     которые
    -0.89
    kanak
    -0.88
    办
    -0.86
    guió
    -0.84
     Betrag
    -0.83
     artikke
    -0.82
     animasi
    -0.82
    POSITIVE LOGITS
     رائ
    0.92
    curity
    0.87
    toolkit
    0.86
    läs
    0.84
    
    0.84
    LECT
    0.83
    ropy
    0.82
    HTTPClient
    0.80
    をご紹介
    0.80
     falando
    0.80
    Activations Density 0.007%

    No Known Activations