© 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. 57690
    Prev
    Next
    INDEX
    Explanations

    granted or denied petitions and reviews

    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
     Lucca
    -0.90
    cetines
    -0.81
    رة
    -0.80
     jurí
    -0.76
     balenciaga
    -0.75
     سر
    -0.73
    ни
    -0.71
     userSchema
    -0.70
    ܣ
    -0.70
    vello
    -0.69
    POSITIVE LOGITS
     granted
    6.31
    granted
    4.81
     grant
    4.41
     granting
    4.34
    grant
    3.97
     grants
    3.94
    Granted
    3.91
     Granted
    3.73
     Grant
    3.56
    Grant
    3.47
    Activations Density 0.125%

    No Known Activations