© 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. 39721
    Prev
    Next
    INDEX
    Explanations

    returns true or show

    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
     the
    -1.89
     I
    -1.67
    ch
    -1.53
    www
    -1.48
    m
    -1.44
    t
    -1.38
    ts
    -1.38
    -
    -1.32
     there
    -1.30
     we
    -1.27
    POSITIVE LOGITS
    πω
    1.34
    剮
    1.34
    Juego
    1.33
     myös
    1.32
    biega
    1.31
     ANOTHER
    1.30
     számára
    1.29
    atás
    1.27
     procesu
    1.27
    Faça
    1.27
    Activations Density 0.017%

    No Known Activations