© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 832
    Prev
    Next
    INDEX
    Explanations

    locations and starting phrases

    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
     youth
    -0.81
    xFE
    -0.79
     chips
    -0.77
    ct
    -0.75
    窗外
    -0.73
     Để
    -0.72
     предела
    -0.71
    atih
    -0.71
    ümüş
    -0.71
    romy
    -0.70
    POSITIVE LOGITS
    VECTOR
    0.79
     TWICE
    0.79
    comfor
    0.78
    ibis
    0.78
    witness
    0.77
    Soo
    0.77
    國民
    0.75
    Dk
    0.75
    specially
    0.74
    误
    0.74
    Activations Density 0.006%

    No Known Activations