© 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. 1368
    Prev
    Next
    INDEX
    Explanations

    websites, tech, landing pages

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

    experience reporting, more favorable, no escape

    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
    ੰਜ
    0.53
    يده
    0.51
    灸
    0.51
    куляр
    0.49
    ലാ
    0.45
    encia
    0.45
    र
    0.45
    終了
    0.44
    なくなる
    0.44
     terve
    0.43
    POSITIVE LOGITS
    Qw
    0.66
    Mb
    0.57
    CLES
    0.52
    Cosine
    0.50
    CharCode
    0.49
    Tree
    0.47
    Qb
    0.47
    Mys
    0.47
    PubKey
    0.46
    Plays
    0.46
    Activations Density 0.000%

    No Known Activations