© 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. 84983
    Prev
    Next
    INDEX
    Explanations

    engine overview, between scenes

    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
     tỏ
    -0.81
     нея
    -0.70
    ôn
    -0.69
    Magnetic
    -0.68
     intereses
    -0.68
    化为
    -0.68
    २
    -0.68
    }}$,
    -0.68
     gondol
    -0.67
    cursion
    -0.66
    POSITIVE LOGITS
     ndi
    0.79
    project
    0.77
    construction
    0.76
    かせて
    0.75
     Circum
    0.74
     esponja
    0.74
     Expressions
    0.73
     subsurface
    0.73
     matériau
    0.71
    ריים
    0.71
    Activations Density 0.010%

    No Known Activations