© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 74005
    Prev
    Next
    INDEX
    Explanations

    range and variation of values

    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_22/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
    strcpy
    -0.89
    ឆ
    -0.82
     duplicated
    -0.78
     dergleichen
    -0.77
     اليابان
    -0.77
    (>
    -0.76
     palju
    -0.74
    ⇀
    -0.74
     distances
    -0.73
    гава
    -0.73
    POSITIVE LOGITS
    ranging
    1.20
     ranging
    1.12
     variations
    1.11
    variations
    1.05
    Variations
    0.99
     anywhere
    0.98
    slightly
    0.98
    InRange
    0.98
     variation
    0.94
     enige
    0.94
    Activations Density 0.057%

    No Known Activations