© 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. 228473
    Prev
    Next
    INDEX
    Explanations

    is possible

    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
    陳
    0.47
     raw
    0.47
    ずっと
    0.46
    ระ
    0.46
     nape
    0.44
     vanilla
    0.43
    ദി
    0.43
    ふ
    0.43
    آ
    0.43
    取り
    0.43
    POSITIVE LOGITS
    arlas
    0.51
    REW
    0.49
    𝙡
    0.49
    тому
    0.49
    TRACK
    0.48
    نيف
    0.47
    itie
    0.46
     عيد
    0.46
    orters
    0.46
    ленном
    0.46
    Activations Density 0.002%

    No Known Activations