© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11370
    Prev
    Next
    INDEX
    Explanations

    future events and releases

    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
    </
    -2.09
    -
    -2.00
     -
    -1.94
    ----------------
    -1.89
    僦
    -1.88
    It
    -1.81
    薷
    -1.80
    蠖
    -1.79
    <td>
    -1.77
    --
    -1.77
    POSITIVE LOGITS
    ஂ
    2.06
    骓
    2.06
     Several
    2.03
     शुर
    1.91
     Those
    1.90
    ઁ
    1.89
    नलोड
    1.88
    งิน
    1.85
    
    1.84
     That
    1.81
    Activations Density 0.007%

    No Known Activations