© 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. 34-GEMMASCOPE-RES-131K
    7. 57186
    Prev
    Next
    INDEX
    Explanations

    using parser in code context

    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_34/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
    ’
    -1.08
    パスワード
    -1.06
     trover
    -1.05
     morti
    -1.02
     Anſ
    -1.00
     nive
    -0.98
     voci
    -0.97
     competen
    -0.90
    ：【
    -0.90
     amounts
    -0.89
    POSITIVE LOGITS
    wanzig
    1.11
    шой
    1.09
    怂
    1.05
    撵
    1.05
    AfterClass
    1.00
     تنا
    1.00
    ﺝ
    0.97
     Ausrüstung
    0.95
    rrrr
    0.93
     asomb
    0.93
    Activations Density 0.005%

    No Known Activations