© 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. 86575
    Prev
    Next
    INDEX
    Explanations

    Horizon Europe programmes and projects

    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
    п
    0.61
     खेळा
    0.57
    бли
    0.54
    гу
    0.54
    <0x80>
    0.52
    ޏ
    0.49
    ᒐ
    0.49
    うん
    0.48
    ᕗ
    0.48
    ਣਾ
    0.47
    POSITIVE LOGITS
     hart
    0.51
    怒
    0.51
     Cál
    0.51
    GA
    0.50
     Calibri
    0.49
    温柔
    0.49
    ES
    0.49
    都不是
    0.49
    织
    0.49
    RE
    0.49
    Activations Density 0.000%

    No Known Activations