© 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. 22-GEMMASCOPE-RES-131K
    7. 33466
    Prev
    Next
    INDEX
    Explanations

    additional works

    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_22/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
    PENDAHULUAN
    -1.09
     huevo
    -1.05
    VIAF
    -1.05
     lixo
    -1.04
     cuchara
    -1.03
     Durchschnitt
    -1.02
     velikost
    -1.02
    zeption
    -1.02
    אר
    -1.02
     vielen
    -1.02
    POSITIVE LOGITS
     of
    1.18
     на
    1.16
    st
    1.10
    “
    1.07
     culturali
    1.03
    <strong>
    1.02
    se
    1.01
     این
    0.99
     О
    0.98
    ěk
    0.97
    Activations Density 0.001%

    No Known Activations