© 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. 91998
    Prev
    Next
    INDEX
    Explanations

    start of a specific phrase

    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
    ják
    -0.97
    スター
    -0.85
    כן
    -0.82
     jagung
    -0.82
     nervous
    -0.81
     accion
    -0.79
    而不
    -0.79
    Canton
    -0.78
     détaillée
    -0.77
    ссию
    -0.74
    POSITIVE LOGITS
     STILL
    1.00
     sowieso
    0.94
    羸
    0.94
     celebró
    0.91
    titue
    0.91
     которым
    0.90
     WHICH
    0.88
    )&&(
    0.88
    ⒝
    0.86
    sburg
    0.85
    Activations Density 0.000%

    No Known Activations