© 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. 7821
    Prev
    Next
    INDEX
    Explanations

    declares clutters decluttering declining clarity clustering unclogging

    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
     స్వా
    0.88
    roh
    0.88
    aste
    0.85
    白的
    0.83
     শৃ
    0.82
    晖
    0.82
    ayd
    0.82
    畏
    0.81
    atorios
    0.80
     whit
    0.80
    POSITIVE LOGITS
    ttino
    1.03
    matically
    0.90
    duel
    0.89
    matics
    0.84
    ttes
    0.84
    gget
    0.83
    currentThread
    0.82
    mes
    0.82
    speople
    0.82
    cter
    0.80
    Activations Density 0.056%

    No Known Activations