Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7763
    Prev
    Next
    INDEX
    Explanations

    come to a conclusion

    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
     '../../../../
    -0.90
     '../../../
    -0.82
    alties
    -0.81
     ligiloj
    -0.80
    ífonos
    -0.78
    koff
    -0.74
    cupine
    -0.73
    了出去
    -0.73
    znacz
    -0.72
    isdigit
    -0.71
    POSITIVE LOGITS
     come
    3.42
     arrive
    3.06
     came
    3.03
     arrived
    2.91
     reach
    2.77
     reached
    2.64
    Come
    2.56
     chegar
    2.55
     comes
    2.52
     arrives
    2.50
    Activations Density 0.074%

    No Known Activations