© 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. 49346
    Prev
    Next
    INDEX
    Explanations

    intolerance attributed to interest

    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
    Wir
    0.50
     Orc
    0.49
    方案
    0.49
     Della
    0.48
     Espí
    0.48
    器
    0.48
    ORS
    0.48
    大赛
    0.47
     Ishikawa
    0.47
    IKV
    0.46
    POSITIVE LOGITS
    (
    0.47
    chess
    0.45
    enn
    0.42
    ப்
    0.41
    .
    0.40
     شد
    0.39
    ound
    0.39
    '
    0.39
    photo
    0.39
     sauvegarde
    0.38
    Activations Density 0.015%

    No Known Activations