© 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. 3109
    Prev
    Next
    INDEX
    Explanations

    defining results or outcomes

    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
    ä
    0.78
    ‌ای
    0.65
    (
    0.63
     travelling
    0.61
    :
    0.61
    ain
    0.59
     tripartite
    0.58
     permeability
    0.56
    ,
    0.55
    ning
    0.55
    POSITIVE LOGITS
    m
    0.78
    al
    0.74
    r
    0.71
    in
    0.70
    ant
    0.67
    p
    0.67
    ين
    0.65
    ла
    0.62
    ec
    0.61
    де
    0.61
    Activations Density 0.276%

    No Known Activations