© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14705
    Prev
    Next
    INDEX
    Explanations

    JavaScript getElementById

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     posizione
    1.16
     adalah
    1.09
     Position
    1.09
    k
    1.07
     quantità
    1.05
    y
    1.04
    hette
    1.03
     Consumption
    1.03
     condizioni
    1.02
    e
    1.02
    POSITIVE LOGITS
     போரா
    1.62
     крупных
    1.58
    raient
    1.56
     एपिस
    1.54
    <unused1864>
    1.54
    Открыть
    1.53
    <unused921>
    1.52
    <unused1899>
    1.51
    崚
    1.51
    <unused793>
    1.49
    Activations Density 0.001%

    No Known Activations