© 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. 3210
    Prev
    Next
    INDEX
    Explanations

    time units and periods

    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
     проце
    -0.76
     voľ
    -0.76
    wählen
    -0.76
    ódz
    -0.74
    loài
    -0.73
     juta
    -0.72
    Lö
    -0.71
    𝓟
    -0.69
     uomo
    -0.69
     detención
    -0.68
    POSITIVE LOGITS
    ęku
    0.79
     when
    0.77
     Recherches
    0.70
     Elke
    0.69
    狮
    0.68
    uló
    0.65
     windings
    0.65
     복
    0.65
     بوابة
    0.65
    ющий
    0.64
    Activations Density 0.012%

    No Known Activations