© 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. 120166
    Prev
    Next
    INDEX
    Explanations

    sharing, technology, Mississippi River

    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
    ghost
    0.41
     മണ്ണി
    0.40
    리소스
    0.40
    我自己
    0.39
    ര്‍ന്ന്
    0.38
    国内外
    0.38
    thousand
    0.38
    
    0.38
     구입
    0.37
     Englishmen
    0.37
    POSITIVE LOGITS
     Sei
    0.44
     sei
    0.41
     Airl
    0.39
     crown
    0.38
    BJ
    0.38
     voorz
    0.38
     lint
    0.38
     sensual
    0.37
    Airport
    0.37
     breakfasts
    0.37
    Activations Density 0.000%

    No Known Activations