© 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. 128683
    Prev
    Next
    INDEX
    Explanations

    best known for or remembered for

    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
     what
    -1.30
     this
    -1.23
     something
    -1.20
     it
    -1.18
     exitosa
    -1.16
     only
    -1.15
     prioridades
    -1.13
     some
    -1.11
     comparatively
    -1.11
     one
    -1.09
    POSITIVE LOGITS
     and
    1.66
     ايران
    1.39
     ſur
    1.14
    𓆏
    1.13
    .
    1.13
     JERSEY
    1.11
     nā
    1.11
     JORDAN
    1.10
     الأحمر
    1.10
     assurent
    1.10
    Activations Density 0.001%

    No Known Activations