© 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. 193501
    Prev
    Next
    INDEX
    Explanations

    guests can

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

    indicates conditions and 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
    ।
    0.56
    ။
    0.53
    नून
    0.52
    ream
    0.51
    သည်။
    0.50
     ভোক্তার
    0.50
     एक्टिंग
    0.50
     продукции
    0.48
    !।
    0.46
    𝘔
    0.46
    POSITIVE LOGITS
     pounding
    0.50
     banging
    0.50
     herm
    0.47
     frequented
    0.43
     isol
    0.42
     masuk
    0.41
     isolation
    0.41
     waging
    0.41
     slightest
    0.41
    readFileSync
    0.41
    Activations Density 0.000%

    No Known Activations