© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107794
    Prev
    Next
    INDEX
    Explanations

    asking for help

    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
     to
    -1.22
     cooperation
    -0.98
     vastly
    -0.98
     vorgenommen
    -0.98
     reliance
    -0.93
    吃了
    -0.93
     многих
    -0.91
     facilmente
    -0.88
     involucrados
    -0.86
     visits
    -0.85
    POSITIVE LOGITS
     out
    2.53
     with
    1.41
     solve
    1.12
     by
    1.09
     Obviously
    1.05
     without
    1.02
    Where
    0.99
    out
    0.97
    criminate
    0.96
    ！（
    0.96
    Activations Density 0.030%

    No Known Activations