© 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. 203656
    Prev
    Next
    INDEX
    Explanations

    cases and insurance benefits

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

    international organizations and technical standards

    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
     λό
    0.57
     אַ
    0.53
     חי
    0.51
     retailing
    0.50
     これ
    0.49
     仮
    0.49
     escudo
    0.47
     値
    0.47
     proletariat
    0.46
    ührung
    0.46
    POSITIVE LOGITS
    }>{
    0.46
    k
    0.45
    lees
    0.44
    最小
    0.44
    build
    0.43
    ர்க
    0.43
    projectId
    0.43
    rások
    0.43
    리의
    0.42
    assist
    0.42
    Activations Density 0.001%

    No Known Activations