© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60573
    Prev
    Next
    INDEX
    Explanations

    code or structure identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    which
    -2.73
    that
    -2.59
    there
    -2.48
    S
    -2.45
    what
    -2.33
     miljoen
    -2.31
     encuent
    -2.27
    by
    -2.25
    lokasi
    -2.22
     gezondheid
    -2.22
    POSITIVE LOGITS
    ↵
    3.97
    渼
    2.84
     ウィメンズ
    2.47
    𖣘
    2.34
    replyreport
    2.34
    峮
    2.30
    鯷
    2.28
     GETTING
    2.25
    ⸂
    2.20
    aneamente
    2.19
    Activations Density 0.164%

    No Known Activations