© 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. 13-GEMMASCOPE-2-RES-16K
    7. 12462
    Prev
    Next
    INDEX
    Explanations

    intuitive fast thinking

    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
    ет
    2.02
    es
    1.83
    肺炎
    1.73
     castration
    1.73
    ्या
    1.70
    sar
    1.63
    𝗲
    1.57
    anthin
    1.55
     divert
    1.54
    ES
    1.53
    POSITIVE LOGITS
    മ്പോൾ
    2.25
    ∂</
    2.02
    ción
    2.00
    هُ
    1.97
    CellStyle
    1.91
    poner
    1.89
     loro
    1.88
     Consiglio
    1.88
    Grazie
    1.86
    teborg
    1.86
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.