© 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. 16-GEMMASCOPE-2-RES-262K
    7. 109246
    Prev
    Next
    INDEX
    Explanations

    pilot programs, projects, trials, testing

    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_16_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
    3
    0.55
     بقول
    0.52
    १०
    0.51
     as
    0.50
    6
    0.50
     国産
    0.49
    cesor
    0.47
    2
    0.47
     бою
    0.46
    сера
    0.46
    POSITIVE LOGITS
    រួម
    0.52
     scab
    0.52
     ماشینونو
    0.51
     paralys
    0.51
    राने
    0.50
     konserv
    0.50
    ாதீர்கள்
    0.50
    ಲಾಯಿತು
    0.50
    特別な
    0.49
     straordin
    0.49
    Activations Density 0.010%

    No Known Activations