© 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. 194317
    Prev
    Next
    INDEX
    Explanations

    certificate or perk

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

    spoken manner of certain things

    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
    t
    0.47
    기
    0.45
    기로
    0.44
     forbade
    0.44
    io
    0.43
     Essence
    0.43
     temperat
    0.43
     '
    0.42
     HOWEVER
    0.42
     아
    0.41
    POSITIVE LOGITS
    града
    0.54
    арма
    0.51
    ĕç
    0.51
    muestra
    0.48
    核心
    0.48
    กรณ์
    0.48
     книга
    0.47
    َه
    0.46
    తిరే
    0.46
     chiesa
    0.45
    Activations Density 0.001%

    No Known Activations