© 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. 119428
    Prev
    Next
    INDEX
    Explanations

    Partnerships and collaborations

    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
    比特
    0.38
    чної
    0.38
    ⤟
    0.38
    谜
    0.37
    Conse
    0.37
    Bishop
    0.37
    Notre
    0.37
    Preliminary
    0.37
    
    0.36
     Obispo
    0.35
    POSITIVE LOGITS
    ad
    0.39
     convertible
    0.38
    ائد
    0.38
     socialist
    0.38
     journalism
    0.37
     wearable
    0.37
     perda
    0.37
    ai
    0.36
    add
    0.36
    cussions
    0.36
    Activations Density 0.021%

    No Known Activations