© 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. 148565
    Prev
    Next
    INDEX
    Explanations

    companies and organizations

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

    nighttime intruder, Nm3/h, management, husband, person

    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
    大
    0.54
    shoes
    0.49
    大佬
    0.47
    jewelry
    0.46
    বসাইট
    0.46
    โจ
    0.45
    ंबकीय
    0.44
    হাসিক
    0.44
    溯
    0.43
    କ
    0.43
    POSITIVE LOGITS
     índ
    0.48
     free
    0.47
     masing
    0.47
     mobili
    0.47
     single
    0.47
     cero
    0.47
     lâng
    0.45
     coloured
    0.45
     bersifat
    0.45
     piani
    0.45
    Activations Density 0.004%

    No Known Activations