© 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. 31469
    Prev
    Next
    INDEX
    Explanations

    Augusta, Georgia

    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
     Priority
    -0.76
    MOC
    -0.76
     tensión
    -0.74
    TTC
    -0.72
    raš
    -0.72
     Caste
    -0.72
    ctc
    -0.70
    zys
    -0.69
    tcb
    -0.68
     Обе
    -0.68
    POSITIVE LOGITS
     Augusta
    0.79
    cessions
    0.78
    🍱
    0.71
     GEORGIA
    0.71
    メイ
    0.71
     Subsid
    0.70
     Godfather
    0.69
     tabloid
    0.69
     penet
    0.68
    ceding
    0.68
    Activations Density 0.014%

    No Known Activations