© 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. 12213
    Prev
    Next
    INDEX
    Explanations

    URL parameters and identifiers

    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
    过去了
    -0.92
    嫫
    -0.86
     that
    -0.84
     lidé
    -0.82
    œurs
    -0.79
    shy
    -0.78
    škoda
    -0.78
    shadowColor
    -0.78
     sué
    -0.78
    𝘸
    -0.78
    POSITIVE LOGITS
     vatt
    0.85
    regardless
    0.75
    ium
    0.74
     boken
    0.74
    同じく
    0.73
    　　　　
    0.73
    especially
    0.73
     répertoire
    0.72
    　　　
    0.72
    <0xC7>
    0.72
    Activations Density 0.071%

    No Known Activations