© 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. 114905
    Prev
    Next
    INDEX
    Explanations

    storage, chassis, holds, personal, visit

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

    code structures and bullet points

    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
     паспорт
    0.45
    ט
    0.45
     mcc
    0.45
     कंप्यूट
    0.45
     ран
    0.45
     മാറി
    0.43
     maintenance
    0.43
    Р
    0.43
     пяти
    0.43
    願い
    0.42
    POSITIVE LOGITS
     Asians
    0.52
    ᚐ
    0.49
    áz
    0.46
     同
    0.44
    uddersfield
    0.44
    ۴
    0.44
     Litter
    0.43
    𝓱
    0.43
     தக்க
    0.43
    fé
    0.42
    Activations Density 0.000%

    No Known Activations