© 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. 134391
    Prev
    Next
    INDEX
    Explanations

    kits, blocks, tablets, customers

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

    describing entities or knowledge

    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
    不仅仅
    0.50
     пен
    0.50
    }{\
    0.46
    🐬
    0.45
     should
    0.44
    ország
    0.44
     -
    0.44
     пови
    0.43
    rások
    0.43
     век
    0.43
    POSITIVE LOGITS
    न्नी
    0.46
    Floor
    0.46
    теру
    0.46
     rik
    0.44
    PPT
    0.43
    єр
    0.43
    ﺻ
    0.43
    Applicant
    0.42
    PROCESSING
    0.42
    ڈا
    0.42
    Activations Density 0.000%

    No Known Activations