© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 870
    Prev
    Next
    INDEX
    Explanations

    I think

    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_13_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
    m
    2.01
    s
    1.97
    с
    1.93
    h
    1.78
    **/
    1.76
    ンジ
    1.73
     Le
    1.69
    w
    1.65
    inating
    1.64
    bearing
    1.64
    POSITIVE LOGITS
    Ｉ
    2.77
     हूं
    2.62
     suppose
    2.54
    RELAND
    2.49
     DISPLAYSURF
    2.48
     wiem
    2.48
    origData
    2.48
     считаю
    2.43
     हूँ
    2.37
    ोजक
    2.37
    Activations Density 0.706%

    No Known Activations