© 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. 58374
    Prev
    Next
    INDEX
    Explanations

    California locations Bakersfield Kern

    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
     goblins
    -0.84
    Namara
    -0.84
     Goblin
    -0.76
    jate
    -0.72
     Turch
    -0.71
     Limerick
    -0.69
     SqlDbType
    -0.68
    Dermott
    -0.66
    COM
    -0.66
    ============
    -0.66
    POSITIVE LOGITS
     Bakersfield
    1.63
     Kern
    1.18
    Kern
    1.04
     Basque
    0.95
     KERN
    0.94
    KERN
    0.90
    kern
    0.88
     Californian
    0.82
     Mojave
    0.82
    BAK
    0.77
    Activations Density 0.017%

    No Known Activations