© 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. 34-GEMMASCOPE-RES-131K
    4. 118979
    Prev
    Next
    INDEX
    Explanations

    nuisance pests, code, versions, licenses

    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
     recomand
    -0.95
    に使用
    -0.93
     loup
    -0.91
     taches
    -0.90
     allons
    -0.90
     avocat
    -0.89
     Ensuite
    -0.89
     belang
    -0.88
     riche
    -0.88
     bruit
    -0.88
    POSITIVE LOGITS
    if
    0.88
     group
    0.82
    })$
    0.80
     again
    0.79
     Here
    0.78
     extensively
    0.78
     single
    0.77
    V
    0.77
     problematic
    0.77
     So
    0.76
    Activations Density 0.001%

    No Known Activations