© 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. 40-GEMMASCOPE-2-RES-262K
    7. 210419
    Prev
    Next
    INDEX
    Explanations

    chinese classical texts

    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_40_width_262k_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
    俸
    0.63
    olojik
    0.60
    邗
    0.56
    🍡
    0.56
    軺
    0.55
    🗡
    0.55
     buddhist
    0.54
    讒
    0.54
    ்ட
    0.54
    亽
    0.54
    POSITIVE LOGITS
     non
    0.46
     therefore
    0.44
    皆
    0.43
    0.43
     wherein
    0.41
     Therefore
    0.40
     flat
    0.40
     V
    0.40
     https
    0.40
    dz
    0.39
    Activations Density 0.003%

    No Known Activations