© 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. 135594
    Prev
    Next
    INDEX
    Explanations

    entity names and attributes

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

    indicating or listing details

    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
    Develop
    0.50
    Rolling
    0.49
    ब
    0.49
    दे
    0.48
    س
    0.48
    ट
    0.47
    Extra
    0.47
    Expanding
    0.46
    Paras
    0.46
    अ
    0.45
    POSITIVE LOGITS
     なさい
    0.59
     কাহারও
    0.52
     Latvij
    0.49
     څرنګوالی
    0.49
     paisaje
    0.49
     forcible
    0.47
     delicioso
    0.47
    šení
    0.47
     Derecho
    0.47
     कितना
    0.46
    Activations Density 0.000%

    No Known Activations