© 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. 50156
    Prev
    Next
    INDEX
    Explanations

    collection, Francisco, query

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

    color, texture, or abstract concepts

    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
     पालन
    0.46
     الخلق
    0.44
     झेल
    0.42
     максимально
    0.42
    楂
    0.40
     التق
    0.40
     kompakt
    0.40
    无可
    0.40
    抟
    0.40
     Vaccine
    0.39
    POSITIVE LOGITS
    巿
    0.46
    iphy
    0.43
    Colors
    0.43
     keb
    0.41
    囉
    0.41
     dupatta
    0.40
    ನ್ನಡ
    0.40
     melodrama
    0.40
     animal
    0.40
    жу
    0.39
    Activations Density 0.000%

    No Known Activations