© 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. 128132
    Prev
    Next
    INDEX
    Explanations

    is a

    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
     with
    -1.15
     and
    -1.12
    P
    -1.05
     it
    -1.04
    F
    -1.02
    삭제
    -1.00
    All
    -0.98
    ěstí
    -0.96
     сборной
    -0.96
    B
    -0.96
    POSITIVE LOGITS
     another
    1.54
     the
    1.52
    はもう
    1.37
     among
    1.35
    で一番
    1.23
     hablado
    1.21
    のひとつ
    1.20
     diharapkan
    1.16
    で大
    1.16
     amongst
    1.14
    Activations Density 0.074%

    No Known Activations