© 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. 178862
    Prev
    Next
    INDEX
    Explanations

    copyright notice, website link, or specific information

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

    safety, shortages, currencies, punctuation

    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
     হবেন
    0.49
     wei
    0.49
    geteilt
    0.46
    竽
    0.43
    荪
    0.43
    医师
    0.42
    ਤ
    0.42
    шив
    0.42
     الجيش
    0.42
     "");
    0.42
    POSITIVE LOGITS
    os
    0.49
     περισσότε
    0.48
    ες
    0.47
     ότι
    0.47
     RELATION
    0.46
    当たり
    0.46
     مرت
    0.45
    abang
    0.45
    PERS
    0.45
    彿
    0.44
    Activations Density 0.000%

    No Known Activations