© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 98908
    Prev
    Next
    INDEX
    Explanations

    beer and editing

    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
    লন
    0.43
     getRandom
    0.40
    োতে
    0.38
     స్టే
    0.38
    
    0.38
    ாத
    0.38
     орби
    0.37
    媺
    0.37
    ividades
    0.36
     লন্ড
    0.36
    POSITIVE LOGITS
    ພວກເຮົາ
    0.39
    택
    0.38
    ᱛ
    0.38
    ligne
    0.37
    <0x87>
    0.37
    ̼
    0.37
    腔
    0.36
    digit
    0.35
     współpracy
    0.35
     chúng
    0.35
    Activations Density 0.000%

    No Known Activations