© 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. 28104
    Prev
    Next
    INDEX
    Explanations

    view, frame, scrollview

    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
    5
    0.64
    вить
    0.59
    3
    0.59
    bahn
    0.59
    ę
    0.58
    9
    0.56
    it
    0.56
     evils
    0.55
    an
    0.54
    czy
    0.54
    POSITIVE LOGITS
    IENCE
    0.63
    Σ
    0.60
    ยู
    0.59
    getImageFolder
    0.58
    Ս
    0.57
    <unused503>
    0.57
    <unused1999>
    0.56
     oth
    0.55
    য্
    0.55
    ពីរ
    0.55
    Activations Density 0.001%

    No Known Activations