© 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. 31-GEMMASCOPE-2-RES-16K
    7. 13583
    Prev
    Next
    INDEX
    Explanations

    keyword research, confidence, budgeting, hypertrophy

    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_31_width_16k_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
    Prob
    0.53
    Plant
    0.42
    Haz
    0.42
    Þ
    0.42
     inconvenience
    0.41
    Illus
    0.41
    Fract
    0.41
    非常に
    0.40
    Prol
    0.40
    虚
    0.39
    POSITIVE LOGITS
     badań
    0.64
     статьи
    0.54
     ちょっと
    0.52
     braucht
    0.52
     ditth
    0.50
    sst
    0.50
     gauges
    0.50
     fileCopy
    0.50
     świata
    0.50
    fwlink
    0.50
    Activations Density 0.059%

    No Known Activations