© 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. 63861
    Prev
    Next
    INDEX
    Explanations

    review copies, IG account, centennial

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

    specific code or terms

    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
    נו
    0.61
    目標
    0.49
    하루
    0.49
    났다
    0.47
    었다
    0.46
    따
    0.46
    កាន់
    0.45
    ው
    0.45
    ثم
    0.45
    شان
    0.44
    POSITIVE LOGITS
     immobil
    0.52
     acceder
    0.51
     mivel
    0.50
     geldig
    0.49
    reen
    0.48
    ív
    0.48
    ret
    0.47
     सदन
    0.47
    ub
    0.46
     consistente
    0.46
    Activations Density 0.000%

    No Known Activations