© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67546
    Prev
    Next
    INDEX
    Explanations

    incrementing numbers

    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
    人たち
    -2.47
     But
    -2.45
    気付
    -2.39
     但
    -2.38
     отличаются
    -2.33
     иметь
    -2.25
    雱
    -2.23
     nhưng
    -2.22
    ときの
    -2.16
    まあ
    -2.14
    POSITIVE LOGITS
    ～！
    2.25
    ’
    2.22
    ),
    2.20
    踅
    2.20
    三月
    2.16
     zahlreiche
    2.11
     邊
    2.11
    ют
    2.11
     believes
    2.09
    璝
    2.09
    Activations Density 0.004%

    No Known Activations