© 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. 47897
    Prev
    Next
    INDEX
    Explanations

    when `then`

    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
    welt
    -0.72
     casera
    -0.69
     acti
    -0.68
    ిం
    -0.66
    Superclass
    -0.65
    endent
    -0.65
    tania
    -0.65
    dife
    -0.65
     subsided
    -0.63
    seteq
    -0.63
    POSITIVE LOGITS
    ;"
    0.73
     Dette
    0.73
    ificador
    0.72
    匡
    0.70
    移動
    0.70
    esterol
    0.68
     whining
    0.67
    pre
    0.67
    线上
    0.67
    anov
    0.66
    Activations Density 0.050%

    No Known Activations