© 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. 110667
    Prev
    Next
    INDEX
    Explanations

    sneak peek, preview

    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
    
    -0.78
    izarre
    -0.76
    Cg
    -0.75
    тового
    -0.74
    apad
    -0.74
    ώ
    -0.73
    identific
    -0.73
    ühne
    -0.72
    cesa
    -0.72
    mii
    -0.71
    POSITIVE LOGITS
     preview
    6.56
    preview
    5.44
    Preview
    4.91
     Preview
    4.88
     previews
    4.84
    PREVIEW
    4.31
     PREVIEW
    3.89
    预览
    3.84
     sneak
    3.81
    Previews
    3.17
    Activations Density 0.069%

    No Known Activations