© 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. 117458
    Prev
    Next
    INDEX
    Explanations

    screening requests, arrange them, all RAM

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

    indicating information in brackets

    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
    _="
    0.54
    ಿದರೆ
    0.51
    מ
    0.51
    人了
    0.49
    م
    0.49
    یی
    0.48
    ڑک
    0.47
    نٹ
    0.46
    ی
    0.46
     presents
    0.46
    POSITIVE LOGITS
    of
    0.53
     nebo
    0.53
    ônia
    0.46
    ofu
    0.45
     Coral
    0.45
     Todos
    0.41
    lobal
    0.40
     Intl
    0.40
     lad
    0.40
    numOf
    0.40
    Activations Density 0.001%

    No Known Activations