© 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. 58060
    Prev
    Next
    INDEX
    Explanations

    BSD license PostgreSQL

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on form‐related security tokens, especially hidden CSRF token fields.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    tarea
    -0.79
    Volker
    -0.76
    instrumental
    -0.73
    striping
    -0.71
    chun
    -0.70
     sideways
    -0.69
     deixar
    -0.69
     Euer
    -0.68
    galvan
    -0.68
    INSTALLATION
    -0.68
    POSITIVE LOGITS
    Mol
    0.72
    За
    0.71
     Pav
    0.71
    ไม
    0.69
     Kv
    0.69
    isNotBlank
    0.68
     تُ
    0.68
    HtmlAttribute
    0.65
     Myrtle
    0.65
    
    0.65
    Activations Density 0.061%

    No Known Activations