© 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. 1677
    Prev
    Next
    INDEX
    Explanations

    simple python scripts

    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
     هنتكلم
    0.39
    枺
    0.37
    laublich
    0.37
    ijdens
    0.34
     протягом
    0.32
     μεγαλ
    0.32
     형태로
    0.32
     گزشتہ
    0.31
     ormai
    0.31
     Öncelikle
    0.31
    POSITIVE LOGITS
    </h1>
    0.57
    Parser
    0.38
    áférés
    0.36
    disamb
    0.34
    дар
    0.34
    <0xE1>
    0.33
     parse
    0.31
    nullable
    0.31
    flug
    0.31
    actoring
    0.31
    Activations Density 0.009%

    No Known Activations