© 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. 109604
    Prev
    Next
    INDEX
    Explanations

    foreign language indicators

    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
    yout
    0.41
     off
    0.39
     pip
    0.39
    <>());
    0.38
    ogyakarta
    0.37
     okun
    0.37
     emig
    0.37
     jose
    0.36
     frame
    0.36
    Bug
    0.36
    POSITIVE LOGITS
    rhinoceros
    0.47
     خير
    0.42
     вели
    0.41
     좋은
    0.40
    ⵎ
    0.39
     Бор
    0.39
    値
    0.39
     ඉතා
    0.39
    价值
    0.38
     По
    0.38
    Activations Density 0.002%

    No Known Activations