© 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. 222181
    Prev
    Next
    INDEX
    Explanations

    swim against

    np_acts-logits-general · gemini-2.5-flash-lite

    clarifying specific points or actions

    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
    anée
    0.51
    sdx
    0.49
    쫌
    0.48
    amides
    0.47
    맏
    0.46
    setAdapter
    0.45
    ம்
    0.45
    Marcus
    0.45
    navigator
    0.44
    mode
    0.44
    POSITIVE LOGITS
    ค
    0.50
     WebDriver
    0.46
     Banking
    0.44
     claim
    0.43
     rewrite
    0.43
     deny
    0.42
     ubiquitous
    0.41
     Salaries
    0.41
    風味
    0.41
     analyze
    0.41
    Activations Density 0.000%

    No Known Activations