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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43022
    Prev
    Next
    INDEX
    Explanations

    names and places

    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
    z
    -3.41
    which
    -2.78
    b
    -2.73
            
    -2.70
     be
    -2.69
                
    -2.61
    厹
    -2.59
     нескольких
    -2.58
    na
    -2.55
    ни
    -2.55
    POSITIVE LOGITS
    ⡪
    2.73
    舢
    2.58
    小镇
    2.50
    ⸒
    2.50
    鼙
    2.30
    釙
    2.25
    湉
    2.25
     она
    2.23
    玏
    2.23
    𝔃
    2.22
    Activations Density 0.013%

    No Known Activations