© 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. 53218
    Prev
    Next
    INDEX
    Explanations

    code snippets and non-English characters

    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
     ٣
    0.58
     మూడు
    0.53
     तीन
    0.53
     iki
    0.50
     ನಲ್ಲಿ
    0.48
     După
    0.48
     değiş
    0.48
     ۳
    0.47
     ۷
    0.47
     बोर्ड
    0.46
    POSITIVE LOGITS
    ου
    0.43
    mathrm
    0.43
                      
    0.43
    ↵
    0.42
    <0xE3>
    0.42
    δε
    0.41
    γν
    0.41
    ॒
    0.41
    λί
    0.39
                                   
    0.39
    Activations Density 0.020%

    No Known Activations