© 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. 210397
    Prev
    Next
    INDEX
    Explanations

    defining extra features

    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
     بینک
    0.44
    Creates
    0.43
    Guarantee
    0.42
    梸
    0.41
    doi
    0.41
    Healthcare
    0.41
     Banque
    0.41
    Innovation
    0.40
     चोपड़ा
    0.40
    Exports
    0.40
    POSITIVE LOGITS
     Tast
    0.42
     DS
    0.38
     ವಿಷಯ
    0.37
     atleast
    0.37
     Knee
    0.37
     പഠ
    0.36
    =""
    0.36
     TDS
    0.36
     surface
    0.36
     ion
    0.36
    Activations Density 0.001%

    No Known Activations