© 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. 86267
    Prev
    Next
    INDEX
    Explanations

    prediction context

    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
    -
    -3.06
    s
    -2.73
    –
    -2.61
    略歴
    -2.44
    カナダ
    -2.44
    作品の
    -2.41
    \
    -2.41
    or
    -2.41
     touted
    -2.33
    老太太
    -2.30
    POSITIVE LOGITS
    媗
    3.16
    抔
    3.13
    箆
    3.06
    
    3.02
    とも言
    2.91
    姈
    2.89
    かなぁ
    2.80
     火锅
    2.72
    嶮
    2.59
    稣
    2.58
    Activations Density 0.002%

    No Known Activations