© 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. 59483
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with numbers

    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
    鳙
    -1.75
    頭髮
    -1.65
     répon
    -1.63
    珹
    -1.55
    考えた
    -1.55
     comptes
    -1.53
    殲
    -1.50
    ächte
    -1.49
     faciliter
    -1.49
    États
    -1.49
    POSITIVE LOGITS
     anymore
    1.68
     in
    1.55
     but
    1.52
    $.
    1.50
    、
    1.46
     mentioning
    1.46
    。
    1.45
     żad
    1.45
    甚至是
    1.42
    3
    1.42
    Activations Density 0.231%

    No Known Activations