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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 28451
    Prev
    Next
    INDEX
    Explanations

    fills, quantity, or completeness

    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
    0
    0.48
    \%,
    0.47
    ０
    0.44
     Перейти
    0.43
    PS
    0.43
    ิศ
    0.42
    ;,
    0.42
    abola
    0.42
    Asian
    0.41
    __,
    0.41
    POSITIVE LOGITS
     ملي
    0.50
     fills
    0.46
    ྭ
    0.44
     etmek
    0.44
     भरना
    0.43
    帽子
    0.43
     fillers
    0.43
    ᓕ
    0.42
    蘄
    0.42
     ట
    0.42
    Activations Density 0.025%

    No Known Activations