© 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. 238232
    Prev
    Next
    INDEX
    Explanations

    radial volume or vs. Play games

    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
    বিড়
    0.49
     আওতায়
    0.47
    CriteriaUtils
    0.46
    日々
    0.44
     местные
    0.44
    প
    0.44
     नगरपालिका
    0.44
     বিপর্যয়
    0.44
     মুজিব
    0.43
     फूट
    0.43
    POSITIVE LOGITS
     so
    0.56
     -
    0.49
     akt
    0.47
    eseen
    0.47
    AI
    0.46
     Qualifying
    0.45
     standpoint
    0.44
     minut
    0.44
    NM
    0.44
     post
    0.43
    Activations Density 0.000%

    No Known Activations