© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 86314
    Prev
    Next
    INDEX
    Explanations

    Delivery Platform

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

    definitions and country data

    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
     इस्लामिक
    0.46
    他
    0.45
     он
    0.43
    这条
    0.43
    世界上最大的
    0.43
    我
    0.43
    伴
    0.43
     режи
    0.41
     তিনিও
    0.41
    假设
    0.41
    POSITIVE LOGITS
    είτε
    0.49
    ți
    0.45
     surtout
    0.45
    ότε
    0.44
    decorators
    0.44
    öy
    0.44
     Ø
    0.44
     samb
    0.44
    ainan
    0.44
    itan
    0.43
    Activations Density 0.000%

    No Known Activations