© 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. 119804
    Prev
    Next
    INDEX
    Explanations

    and Y

    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
     "
    -2.13
     pemimpin
    -1.58
     rekan
    -1.52
    ?
    -1.49
     ".
    -1.48
    ㅎ
    -1.41
     Emeritus
    -1.41
     if
    -1.41
     or
    -1.38
     Both
    -1.36
    POSITIVE LOGITS
     quella
    1.83
    ,“
    1.74
    НОГО
    1.59
     múltiples
    1.55
    ….”
    1.55
    躥
    1.54
    Ꮟ
    1.54
     möjligt
    1.53
     adequado
    1.53
    都有
    1.49
    Activations Density 0.031%

    No Known Activations