© 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. 78930
    Prev
    Next
    INDEX
    Explanations

    ```code delimiters and start tokens```

    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
    Aviso
    -0.75
    idak
    -0.75
     comple
    -0.68
    φέρ
    -0.68
    Batt
    -0.68
    ynh
    -0.68
     butt
    -0.68
     stain
    -0.67
     épic
    -0.67
     straightforward
    -0.66
    POSITIVE LOGITS
    Cls
    0.83
     civile
    0.81
    تاریخ
    0.79
    tious
    0.77
     mesto
    0.77
    orship
    0.76
    🏏
    0.76
    сса
    0.75
    orama
    0.75
     hasattr
    0.74
    Activations Density 0.015%

    No Known Activations