Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 11193
    Prev
    Next
    INDEX
    Explanations

    LoRA

    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
    ation
    0.55
     s
    0.54
     ந
    0.54
     см
    0.53
     बढ़े
    0.53
     उपलब्ध
    0.53
     rebounding
    0.52
    awanda
    0.52
     press
    0.51
     Sapphire
    0.51
    POSITIVE LOGITS
     geometri
    0.51
     worshipped
    0.50
    жить
    0.49
     THEY
    0.49
    道德
    0.49
    Classical
    0.48
    當時
    0.48
    チル
    0.48
    ῷ
    0.48
    мо
    0.47
    Activations Density 0.003%

    No Known Activations