© 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. 41696
    Prev
    Next
    INDEX
    Explanations

    sliding effect and transitions

    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
    from
    -2.34
    G
    -2.09
    <em>
    -2.09
    d
    -2.05
    s
    -2.03
    0
    -2.00
    k
    -1.95
    2
    -1.89
    o
    -1.88
    na
    -1.84
    POSITIVE LOGITS
    汌
    2.36
    
    2.22
    𐬹
    2.06
     fundada
    2.03
    𓁹
    2.00
    ৢ
    1.97
     entrevist
    1.97
    ᚔ
    1.95
     esperan
    1.94
    
    1.93
    Activations Density 0.020%

    No Known Activations