© 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. 48806
    Prev
    Next
    INDEX
    Explanations

    location coordinates

    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
    苫
    -0.75
    बाह
    -0.75
    uint
    -0.72
     актер
    -0.71
    Click
    -0.71
     année
    -0.69
    petal
    -0.68
    மி
    -0.67
    uwe
    -0.67
    gunt
    -0.67
    POSITIVE LOGITS
     provider
    1.19
     providers
    1.15
     GPS
    1.13
     gps
    1.09
    providers
    1.08
     Provider
    1.05
     Providers
    1.02
     location
    1.01
    GPS
    0.97
     NETWORK
    0.96
    Activations Density 0.013%

    No Known Activations