© 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. 22-GEMMASCOPE-2-RES-16K
    7. 7836
    Prev
    Next
    INDEX
    Explanations

    here followed by quote

    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_22_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
     ذریعے
    0.91
    intre
    0.91
    gs
    0.90
    seek
    0.87
    dove
    0.86
    asth
    0.86
    ¡
    0.85
    حث
    0.85
    vict
    0.85
     zs
    0.84
    POSITIVE LOGITS
     Notion
    0.97
    Ratio
    0.89
     Harmonic
    0.87
    тності
    0.87
     Ratio
    0.87
     bene
    0.85
     COUNT
    0.84
     countDown
    0.83
     coefficients
    0.82
     Crude
    0.82
    Activations Density 0.002%

    No Known Activations