© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 228413
    Prev
    Next
    INDEX
    Explanations

    arrival of precursors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Barr
    0.52
    Flush
    0.51
    IsOpen
    0.51
    Airport
    0.50
     интернет
    0.50
    Timeout
    0.50
    ('$
    0.49
     Бан
    0.48
    DateTimeField
    0.48
    StringUtils
    0.47
    POSITIVE LOGITS
     a
    0.51
     please
    0.51
     delegated
    0.50
     para
    0.48
     stron
    0.48
     stipulated
    0.48
     an
    0.47
     another
    0.46
     simile
    0.46
     humoral
    0.46
    Activations Density 0.001%

    No Known Activations