© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11443
    Prev
    Next
    INDEX
    Explanations

    extent and attribution of qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __':
    -0.81
     apoy
    -0.80
     viele
    -0.79
    щите
    -0.78
    となり
    -0.76
    OOTDTY
    -0.75
    ที่สุด
    -0.74
     estratég
    -0.74
    емой
    -0.73
    骸
    -0.73
    POSITIVE LOGITS
    それだけ
    1.26
     testament
    1.15
     tellement
    1.02
     настолько
    0.94
    typeof
    0.89
    seamnă
    0.87
    Only
    0.86
    æ
    0.86
    可见
    0.86
    いかに
    0.86
    Activations Density 0.031%

    No Known Activations