© 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. 209739
    Prev
    Next
    INDEX
    Explanations

    children, families, and dogs

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

    phrases with specific grammatical structures

    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
     luminos
    0.49
     ただ
    0.48
     temporal
    0.46
     demonstrable
    0.46
     スペ
    0.46
     mė
    0.45
     (°
    0.45
    𝒇
    0.45
     étudiant
    0.44
     serupa
    0.44
    POSITIVE LOGITS
    ве
    0.57
    蹙
    0.54
    в
    0.52
    的意思
    0.50
    хи
    0.50
    u
    0.50
    ु
    0.49
    t
    0.48
     xml
    0.47
    战场
    0.47
    Activations Density 0.000%

    No Known Activations