© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 142075
    Prev
    Next
    INDEX
    Explanations

    extracting code or data

    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
    ܸ
    0.50
    स
    0.49
    युक्त
    0.48
    যুক্ত
    0.48
    би
    0.48
    ปรุง
    0.45
     semn
    0.45
     telo
    0.45
    ͕
    0.45
    راجع
    0.45
    POSITIVE LOGITS
    ion
    0.55
    დან
    0.49
    ande
    0.48
     largely
    0.46
     φορά
    0.46
    8
    0.46
    iz
    0.46
    imax
    0.46
    idać
    0.46
     and
    0.46
    Activations Density 0.000%

    No Known Activations