© 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. 52341
    Prev
    Next
    INDEX
    Explanations

    for durations

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

    tools, rentals, variations, route

    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
    convert
    0.45
    簡単に
    0.43
    㬶
    0.43
    interacting
    0.43
    lighting
    0.42
     converting
    0.42
     massac
    0.42
    excitation
    0.42
    보면
    0.42
    不過
    0.41
    POSITIVE LOGITS
     टाइगर
    0.47
     Embed
    0.46
     previsto
    0.45
    King
    0.45
     Ships
    0.45
    Coach
    0.44
    ଟ
    0.44
     স্বভাব
    0.43
     rencana
    0.43
     texId
    0.43
    Activations Density 0.000%

    No Known Activations