© 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. 13383
    Prev
    Next
    INDEX
    Explanations

    variable names after type

    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
     into
    -1.68
     even
    -1.55
     on
    -1.45
     nawet
    -1.42
     vertraut
    -1.20
    страя
    -1.19
     through
    -1.18
     across
    -1.13
     now
    -1.13
    的重要
    -1.12
    POSITIVE LOGITS
     than
    1.40
    他们在
    1.35
    enance
    1.31
    cising
    1.30
     orice
    1.27
     maman
    1.26
     tuturor
    1.24
    erun
    1.24
    vertis
    1.23
     dehors
    1.23
    Activations Density 0.008%

    No Known Activations