© 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. 57989
    Prev
    Next
    INDEX
    Explanations

    FLAG ACTIVITY CLEAR SINGLE

    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
     произ
    -0.79
    enské
    -0.78
     kidnapped
    -0.76
    telecom
    -0.76
    genöss
    -0.75
     रेट
    -0.75
    ersonic
    -0.75
    otis
    -0.74
     aprovecha
    -0.74
     requested
    -0.74
    POSITIVE LOGITS
     clear
    0.98
    CLEAR
    0.97
     Clearing
    0.94
     очи
    0.93
     clearing
    0.92
     clears
    0.91
     FLAG
    0.84
    Clear
    0.83
    FLAG
    0.79
    clear
    0.79
    Activations Density 0.007%

    No Known Activations