© 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. 65394
    Prev
    Next
    INDEX
    Explanations

    special characters followed by alphanumeric sequences

    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
     or
    -1.93
     because
    -1.84
     using
    -1.83
     what
    -1.79
     at
    -1.74
     get
    -1.73
     taking
    -1.73
     these
    -1.67
     with
    -1.65
     making
    -1.63
    POSITIVE LOGITS
     momentous
    1.85
     horrid
    1.85
     fantastic
    1.83
     delightful
    1.78
     opulent
    1.77
     terrific
    1.76
     magnificent
    1.76
     exceedingly
    1.74
     exceptionally
    1.71
     fabulous
    1.70
    Activations Density 0.012%

    No Known Activations