© 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. 97986
    Prev
    Next
    INDEX
    Explanations

    code generation comments

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     порядке
    -0.75
    🗒
    -0.68
     snabbt
    -0.68
    zeiro
    -0.67
     hvert
    -0.66
    Typed
    -0.65
     stylu
    -0.64
    Rae
    -0.64
    contrib
    -0.63
     kym
    -0.63
    POSITIVE LOGITS
     wrapper
    0.82
    认知
    0.74
     exposed
    0.74
    WRAPPER
    0.73
    Exposed
    0.73
    wrapper
    0.72
     Kanto
    0.68
     sinal
    0.66
     Vitamin
    0.66
     Exposed
    0.66
    Activations Density 0.071%

    No Known Activations