© 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. 79027
    Prev
    Next
    INDEX
    Explanations

    investigation or detection

    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
     $-
    -0.96
     -
    -0.91
    usses
    -0.87
     –
    -0.87
    されていない
    -0.86
     use
    -0.85
    していない
    -0.81
    entras
    -0.81
    ████
    -0.81
     would
    -0.81
    POSITIVE LOGITS
    ständige
    0.97
    ahora
    0.97
     angelegt
    0.93
    ständig
    0.92
     erbjuder
    0.91
    möbel
    0.90
     casamento
    0.86
    鈑
    0.84
    Caratter
    0.82
     menina
    0.82
    Activations Density 0.002%

    No Known Activations