© 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. 118635
    Prev
    Next
    INDEX
    Explanations

    code loops and variables

    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
    後的
    -0.88
     Handlung
    -0.86
     nov
    -0.81
     Spike
    -0.81
     ANY
    -0.80
    óry
    -0.79
     sportowe
    -0.77
     palavra
    -0.76
     declaração
    -0.75
     pada
    -0.75
    POSITIVE LOGITS
    lelő
    0.84
    ciata
    0.77
     můžete
    0.75
    定食
    0.75
     dll
    0.75
    Falta
    0.74
     NICE
    0.74
    zech
    0.73
    ذت
    0.72
    ويد
    0.71
    Activations Density 0.002%

    No Known Activations