© 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. 3325
    Prev
    Next
    INDEX
    Explanations

    captions for images

    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
    t
    1.68
    h
    1.27
    д
    1.14
    q
    1.12
    स
    1.04
    د
    1.03
    ;
    1.02
    z
    1.01
     искать
    1.00
    s
    1.00
    POSITIVE LOGITS
    5
    1.33
    يد
    1.20
    不
    1.19
    م
    1.16
    8
    1.16
    4
    1.13
    for
    1.13
    7
    1.13
    ो
    1.12
    an
    1.06
    Activations Density 0.017%

    No Known Activations