© 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. 64268
    Prev
    Next
    INDEX
    Explanations

    More than, More and, More VC

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

    predicting word sequences

    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
    Á
    0.48
    modations
    0.48
    SMALL
    0.46
    een
    0.45
    AL
    0.45
    यह
    0.45
    এ
    0.45
    מ
    0.45
    他的
    0.45
    Information
    0.45
    POSITIVE LOGITS
     harvest
    0.44
     یقین
    0.42
     schematically
    0.41
    ওল
    0.40
     subsistence
    0.39
     Tây
    0.39
     pigmented
    0.39
    틱
    0.39
    PAS
    0.39
     coexist
    0.39
    Activations Density 0.001%

    No Known Activations