© 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. 110515
    Prev
    Next
    INDEX
    Explanations

    feeder, starter, spinner, finder, shooter

    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
     īpa
    -0.85
    recursos
    -0.82
     essenziale
    -0.82
     galima
    -0.80
    罵
    -0.79
    stel
    -0.79
     玻璃
    -0.79
     asmen
    -0.77
     בפ
    -0.77
    rinha
    -0.77
    POSITIVE LOGITS
    oo
    1.24
    alogy
    1.02
    ific
    1.00
    ised
    0.98
    ize
    0.98
    ized
    0.95
    ight
    0.94
     приведен
    0.92
    gebnis
    0.90
    ator
    0.83
    Activations Density 0.062%

    No Known Activations