© 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. 6694
    Prev
    Next
    INDEX
    Explanations

    Microsoft Excel reports and assistance

    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
    ᖕ
    0.31
     मार्केटिंग
    0.27
     salespeople
    0.26
     सर्जन
    0.25
     sepen
    0.25
    𒌅
    0.24
    étera
    0.24
     totalPrice
    0.24
     মার্কেটিং
    0.24
     стратеги
    0.24
    POSITIVE LOGITS
     Excel
    0.31
    Excel
    0.30
    Excellent
    0.29
     Excellent
    0.27
     Bachelor
    0.26
     reports
    0.26
     Assists
    0.26
     Assist
    0.26
     D
    0.25
     excellent
    0.25
    Activations Density 0.024%

    No Known Activations