© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 38535
    Prev
    Next
    INDEX
    Explanations

    Qt classes and declarations

    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
     California
    -1.38
     your
    -1.34
     opinie
    -1.30
     our
    -1.27
     マフラー
    -1.23
     Józef
    -1.21
     meille
    -1.20
    ooga
    -1.19
    ucson
    -1.16
     hemd
    -1.16
    POSITIVE LOGITS
    مدیر
    1.36
    የ
    1.35
    ⾼
    1.28
    Благодаря
    1.22
    مقال
    1.20
     colina
    1.16
     anys
    1.16
     pilar
    1.15
     acon
    1.13
     Gabor
    1.10
    Activations Density 0.040%

    No Known Activations