© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 14018
    Prev
    Next
    INDEX
    Explanations

    specific examples or categories

    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
     רי
    0.44
     פר
    0.44
    OCKET
    0.42
     구
    0.42
     슬
    0.42
     любы
    0.41
    𝘫
    0.41
     モ
    0.41
     учиты
    0.41
    ত্যার
    0.41
    POSITIVE LOGITS
    ware
    0.38
     chẳng
    0.37
    ’
    0.37
    purpose
    0.36
    ajući
    0.36
    cand
    0.36
    jpa
    0.36
    —
    0.36
     whopping
    0.36
    ueur
    0.35
    Activations Density 0.041%

    No Known Activations