© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11472
    Prev
    Next
    INDEX
    Explanations

    Q: followed by text

    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
     yyb
    -1.66
     pistolet
    -1.53
    dengan
    -1.49
     観光
    -1.45
     aktivitet
    -1.43
     memasak
    -1.41
     algas
    -1.41
    ネ
    -1.41
     бампер
    -1.40
     dårlig
    -1.38
    POSITIVE LOGITS
    al
    1.70
    了些
    1.56
    了一些
    1.54
    u
    1.44
    ar
    1.43
    er
    1.43
     _________
    1.37
     .......
    1.34
     schonmal
    1.32
    n
    1.32
    Activations Density 0.000%

    No Known Activations