© 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. 7926
    Prev
    Next
    INDEX
    Explanations

    CSI Effect, uci show, pci, Lumi

    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
    ن
    0.61
    യുള്ള
    0.58
    కు
    0.57
    ‌కు
    0.54
    iaxial
    0.50
    িপ
    0.50
    నూ
    0.50
    ను
    0.50
    ione
    0.49
    ah
    0.49
    POSITIVE LOGITS
    ゅう
    0.95
    깐
    0.90
    ょう
    0.77
    ņš
    0.72
    ゅ
    0.70
    ぃ
    0.68
    ye
    0.66
    ğin
    0.64
    ya
    0.63
    ゃ
    0.63
    Activations Density 0.089%

    No Known Activations