© 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. 20887
    Prev
    Next
    INDEX
    Explanations

    ready to act or discuss

    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
    ine
    0.70
    s
    0.70
    inating
    0.69
    iendo
    0.61
    estimated
    0.61
    isering
    0.61
    IC
    0.60
    ים
    0.59
    aid
    0.59
    a
    0.59
    POSITIVE LOGITS
    ва
    0.66
     \
    0.64
     DeConcini
    0.58
     hypertro
    0.57
     controle
    0.57
     politique
    0.55
     Cartan
    0.54
     religione
    0.54
     в
    0.53
     т
    0.52
    Activations Density 0.006%

    No Known Activations