© 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. 60610
    Prev
    Next
    INDEX
    Explanations

    need doing, home moving

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

    Alert Description

    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
     Pasc
    0.52
    Г
    0.46
     Ото
    0.45
    spot
    0.44
     nascent
    0.44
     ご
    0.43
     送料無料
    0.43
     П
    0.43
    utos
    0.43
    +
    0.43
    POSITIVE LOGITS
    ymmetries
    0.49
    浓度
    0.48
    🎱
    0.48
    发生的
    0.47
     همد
    0.46
    🔷
    0.46
    剧中
    0.46
    <unused88>
    0.46
    ักษ
    0.45
    লভ
    0.45
    Activations Density 0.000%

    No Known Activations