© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 25141
    Prev
    Next
    INDEX
    Explanations

    words with suffixes or specific names

    np_acts-logits-general · gemini-2.5-flash-lite

    n

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    ু
    0.93
    dır
    0.86
    0.83
    sunday
    0.81
    ي
    0.80
    s
    0.80
     jugador
    0.77
    ه
    0.76
    ી
    0.76
    salaryfrom
    0.75
    POSITIVE LOGITS
    il
    0.82
    me
    0.79
    مون
    0.79
    ens
    0.77
    ਮ
    0.75
     an
    0.74
    ز
    0.74
    iden
    0.72
    un
    0.72
    قد
    0.72
    Activations Density 0.135%

    No Known Activations