© 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. 103534
    Prev
    Next
    INDEX
    Explanations

    Indian followed by institutions and entities

    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
    '
    -3.95
    on
    -3.13
     he
    -2.92
     enam
    -2.52
    \
    -2.50
    to
    -2.39
    ↵
    -2.38
    and
    -2.31
     социаль
    -2.27
     I
    -2.20
    POSITIVE LOGITS
    翾
    2.89
    蒌
    2.75
    悒
    2.59
    طبيق
    2.52
     pneu
    2.50
    艫
    2.50
     broderie
    2.41
     faſt
    2.36
     techniczne
    2.33
     misteriosa
    2.33
    Activations Density 0.021%

    No Known Activations