© 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. 3770
    Prev
    Next
    INDEX
    Explanations

    forms, model, and input binding

    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
     inteiro
    0.56
    abá
    0.50
     এক্ষ
    0.49
     heli
    0.48
    hesi
    0.47
    Agora
    0.46
    雵
    0.46
    <unused79>
    0.46
     jär
    0.46
     nvidia
    0.46
    POSITIVE LOGITS
     blames
    0.60
    ̀
    0.59
    ι
    0.58
     FormGroup
    0.56
    ी
    0.55
    uous
    0.55
    л
    0.54
    ɳ
    0.54
     hopes
    0.54
    Ꮠ
    0.54
    Activations Density 0.010%

    No Known Activations