© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71481
    Prev
    Next
    INDEX
    Explanations

    starts with "not" or "nothing"

    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
     rése
    -1.91
    稣
    -1.75
    茈
    -1.74
     wonderful
    -1.59
    蠵
    -1.59
     juſ
    -1.56
    鈀
    -1.55
     SEVENT
    -1.55
     wonderfully
    -1.54
    蹀
    -1.53
    POSITIVE LOGITS
    ’
    1.73
     starts
    1.58
     
    1.56
     with
    1.48
     without
    1.38
     begin
    1.38
     f
    1.38
     “
    1.37
     b
    1.33
    id
    1.33
    Activations Density 0.079%

    No Known Activations