© 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. 96594
    Prev
    Next
    INDEX
    Explanations

    official, group, director, classes

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

    acknowledging inherent complexities

    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
    IGNORE
    0.45
    模式
    0.44
     plástico
    0.43
     frigor
    0.43
    पाकिस्तान
    0.42
    yster
    0.41
    マ
    0.41
    роятно
    0.41
    宿
    0.40
    时间
    0.40
    POSITIVE LOGITS
    gage
    0.47
     공식
    0.47
    ობს
    0.47
    gence
    0.46
    official
    0.46
     Ці
    0.46
    敕
    0.45
    director
    0.45
     뿌
    0.44
    d
    0.44
    Activations Density 0.002%

    No Known Activations