© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3506
    Prev
    Next
    INDEX
    Explanations

    expected number

    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
    価値
    1.80
    SQL
    1.77
    트워크
    1.62
     Kirk
    1.59
    ้อย
    1.58
    er
    1.57
    邈
    1.57
     製品
    1.57
    ה
    1.55
    POSED
    1.54
    POSITIVE LOGITS
    akata
    1.92
    akarane
    1.79
    Personensuche
    1.79
    induction
    1.76
    arete
    1.72
    ertel
    1.71
    urup
    1.70
    encije
    1.70
    iala
    1.69
     auxqu
    1.66
    Activations Density 0.000%

    No Known Activations