© 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. 17450
    Prev
    Next
    INDEX
    Explanations

    shruti haasan ; furthermore

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

    codes and definitions

    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
    िसा
    0.45
     '
    0.42
     -
    0.40
     ('
    0.39
     juge
    0.39
    _'
    0.39
    怡
    0.39
     oeuvre
    0.39
     কারও
    0.39
     -"
    0.38
    POSITIVE LOGITS
    <h4>
    0.45
    –
    0.43
    <h5>
    0.42
     esperamos
    0.41
     Checkout
    0.41
     DOWNLOAD
    0.40
    ➧
    0.39
     हमरे
    0.39
    ′-
    0.39
    .–
    0.38
    Activations Density 0.100%

    No Known Activations