© 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. 30786
    Prev
    Next
    INDEX
    Explanations

    kot/gott followed by specific endings

    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
    ຕິດຕ
    0.39
     Фи
    0.37
     క్ష
    0.37
     Woodford
    0.37
    ,_-
    0.36
    🗑
    0.36
    uvian
    0.36
    જન
    0.35
    民
    0.35
     सदस्यों
    0.34
    POSITIVE LOGITS
    </a>
    0.38
    
    0.38
     conviction
    0.38
    ียร์
    0.38
     questionnaire
    0.36
     Doctrine
    0.36
     Compagnie
    0.35
    жих
    0.34
    doctrine
    0.34
    kas
    0.33
    Activations Density 0.001%

    No Known Activations