© 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. 65191
    Prev
    Next
    INDEX
    Explanations

    presence

    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
    蟥
    -2.92
    鲞
    -2.67
    x
    -2.63
     Gründen
    -2.58
     verfügb
    -2.50
     haupts
    -2.47
    -2.42
     Dinas
    -2.31
    ౭
    -2.28
    </i>
    -2.27
    POSITIVE LOGITS
    Ито
    2.75
    ஂ
    2.67
     in
    2.52
    Quiero
    2.41
    งิน
    2.34
    瑧
    2.33
    ﹶ
    2.31
    Плюсы
    2.30
    ꪻ
    2.28
    Выводы
    2.25
    Activations Density 0.018%

    No Known Activations