© 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. 236507
    Prev
    Next
    INDEX
    Explanations

    vacuum storage, give colour, categories, Crisis

    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
     '
    0.44
     deductive
    0.43
    kee
    0.41
     હતા
    0.40
    explo
    0.40
     क्वा
    0.39
    µ
    0.39
    unia
    0.39
    閉
    0.38
    frig
    0.38
    POSITIVE LOGITS
    ᒃ
    0.49
    <unused10>
    0.49
     irrevers
    0.49
     irrevoc
    0.49
    ებისთვის
    0.48
     проекту
    0.48
     Secondo
    0.48
     Söz
    0.47
    爣
    0.47
    マグ
    0.47
    Activations Density 0.001%

    No Known Activations