© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 65021
    Prev
    Next
    INDEX
    Explanations

    ization / isation / ize

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    も
    0.66
    s
    0.64
    6
    0.63
    ssä
    0.63
    1
    0.63
    ים
    0.61
    sorted
    0.60
    5
    0.56
    گی
    0.55
    ski
    0.53
    POSITIVE LOGITS
    و
    0.62
     hóa
    0.61
    化的
    0.61
    ilization
    0.61
     hoá
    0.54
    <0x80>
    0.54
    н
    0.54
     शाय
    0.53
    isation
    0.52
    лизация
    0.52
    Activations Density 0.238%

    No Known Activations