© 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. 34-GEMMASCOPE-RES-131K
    7. 118968
    Prev
    Next
    INDEX
    Explanations

    cra prefix words (crabs, crave, crass, craved, craigslist)

    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_34/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
    女朋友
    -0.85
     comprometido
    -0.82
     usual
    -0.82
    缴
    -0.77
     aján
    -0.77
     Öffentlich
    -0.76
     всичко
    -0.76
    pected
    -0.76
     niew
    -0.74
    竊
    -0.73
    POSITIVE LOGITS
     cra
    1.74
     Cra
    1.63
    Cra
    1.62
    cra
    1.51
     crabs
    1.03
     cras
    1.02
     Cramer
    1.02
    🦀
    1.02
     CRA
    1.00
    CRA
    1.00
    Activations Density 0.016%

    No Known Activations