© 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. 22-GEMMASCOPE-RES-131K
    7. 11158
    Prev
    Next
    INDEX
    Explanations

    efficiently, operations, ways

    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_22/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
     exceptionally
    -3.09
     insanely
    -2.92
     predominantly
    -2.89
     strikingly
    -2.86
     pivotal
    -2.86
     exceptional
    -2.84
     renowned
    -2.83
     terrific
    -2.78
     amazingly
    -2.73
     delightfully
    -2.67
    POSITIVE LOGITS
     While
    2.47
     Despite
    2.36
     δεν
    2.33
     Although
    2.31
     ONLY
    2.27
    壺
    2.22
    стреча
    2.19
     wants
    2.19
     brune
    2.19
     Those
    2.17
    Activations Density 0.023%

    No Known Activations