© 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-262K
    7. 39964
    Prev
    Next
    INDEX
    Explanations

    breakdown of how to confirm

    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_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
    recruit
    0.50
     Corrosion
    0.50
     Module
    0.46
     Arun
    0.44
    ü
    0.44
     RoHS
    0.43
    simulate
    0.43
     Boards
    0.43
     байгаа
    0.43
    Cryptography
    0.43
    POSITIVE LOGITS
    ০০
    0.46
    ו
    0.46
     handling
    0.42
     abges
    0.41
     שב
    0.40
     valuations
    0.40
     routing
    0.40
     précie
    0.39
    जिया
    0.39
     yerde
    0.39
    Activations Density 0.000%

    No Known Activations