© 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. 10-GEMMASCOPE-RES-131K
    7. 10030
    Prev
    Next
    INDEX
    Explanations

    words starting with Bl

    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_10/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
    ↵↵
    -3.25
    逦
    -2.97
    is
    -2.80
    it
    -2.70
    雳
    -2.55
    髏
    -2.41
    薷
    -2.33
    <em>
    -2.30
    ſelves
    -2.25
    इस
    -2.25
    POSITIVE LOGITS
    ໊
    3.02
     '
    2.97
    ?"
    2.92
    烀
    2.63
    ⧠
    2.58
     iſt
    2.53
    嗩
    2.50
    
    2.47
    鳢
    2.47
    umumkan
    2.42
    Activations Density 0.006%

    No Known Activations