© 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. 199942
    Prev
    Next
    INDEX
    Explanations

    selective picking of evidence

    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
    గాలు
    0.46
     команды
    0.45
    参见
    0.45
    ૬
    0.45
    事项
    0.44
    ریم
    0.44
     స్వాధీ
    0.43
    preter
    0.43
     comand
    0.42
    缅
    0.42
    POSITIVE LOGITS
     období
    0.48
    ቂ
    0.47
     ž
    0.44
     বর্তমানে
    0.44
     বয়স
    0.43
     দীর্ঘ
    0.42
     ژ
    0.42
     ض
    0.41
     বর্তমান
    0.41
     Má
    0.41
    Activations Density 0.001%

    No Known Activations