© 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. 104753
    Prev
    Next
    INDEX
    Explanations

    sales fee, double glazed, during Holy, the IRS

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

    own specific

    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
     шесть
    0.49
    闕
    0.48
    েন
    0.48
    ボトル
    0.47
    停車
    0.47
     வலியுறு
    0.47
     Ն
    0.46
    ැල
    0.46
    льными
    0.45
     பள்ளத்தா
    0.45
    POSITIVE LOGITS
    aa
    0.51
    tv
    0.47
    s
    0.47
    swan
    0.46
    ^^
    0.45
    unn
    0.45
     Ald
    0.44
    yer
    0.44
     altra
    0.44
    resp
    0.44
    Activations Density 0.001%

    No Known Activations