© 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. 159334
    Prev
    Next
    INDEX
    Explanations

    following commands and conditions

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

    headings in web pages

    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
     কম
    0.56
    ępow
    0.54
    л
    0.51
    е
    0.48
    я
    0.47
     মাতৃ
    0.46
    UserController
    0.45
    PerTrial
    0.45
    วน
    0.45
    что
    0.45
    POSITIVE LOGITS
     happenings
    0.52
     trusts
    0.43
     Sayles
    0.42
     ਇ
    0.41
    事情
    0.41
     unpleasant
    0.40
    ECT
    0.39
    adia
    0.39
     antis
    0.38
    ന്തു
    0.38
    Activations Density 0.001%

    No Known Activations