© 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. 66938
    Prev
    Next
    INDEX
    Explanations

    list or tensor indexing

    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
     not
    -1.63
     capucha
    -1.22
     هستیم
    -1.20
     treno
    -1.16
     soldati
    -1.16
     بودند
    -1.13
     Benutz
    -1.12
    ಱ
    -1.12
     virkelig
    -1.11
    襤
    -1.09
    POSITIVE LOGITS
     of
    1.69
     všetky
    1.33
     ägg
    1.31
     sözler
    1.27
     всех
    1.24
     —
    1.23
     posible
    1.20
    Entrevista
    1.18
    VENTORY
    1.16
     is
    1.16
    Activations Density 0.029%

    No Known Activations