© 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. 74105
    Prev
    Next
    INDEX
    Explanations

    bear fruit

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

    inflation bug, extra damage, approval

    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
    h
    0.55
    the
    0.48
    to
    0.46
     himself
    0.45
    stä
    0.45
     therapies
    0.44
     extended
    0.43
    alter
    0.43
     Ö
    0.43
     altered
    0.42
    POSITIVE LOGITS
    အစိတ်အပိုင်း
    0.46
     păr
    0.46
    银行
    0.46
    穩定
    0.46
     hémorro
    0.45
    uyền
    0.44
    瑭
    0.44
    囟
    0.44
     হোট
    0.44
     компонентов
    0.44
    Activations Density 0.001%

    No Known Activations