© 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. 12481
    Prev
    Next
    INDEX
    Explanations

    from the moment or time

    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
     aporte
    -1.65
    从此
    -1.63
     help
    -1.60
    ㈱
    -1.58
    儼
    -1.56
     höheren
    -1.55
    躊
    -1.52
     sốt
    -1.51
     revised
    -1.49
     einzigen
    -1.49
    POSITIVE LOGITS
     afar
    2.00
     to
    1.98
    真的很
    1.80
    t
    1.72
    必然
    1.69
    viously
    1.68
    jména
    1.66
    pplung
    1.65
     juſ
    1.64
     "..\..\..\
    1.63
    Activations Density 0.021%

    No Known Activations