© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 58285
    Prev
    Next
    INDEX
    Explanations

    author names and initials

    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_34/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
     maniere
    -1.82
    有问题
    -1.70
     préférences
    -1.69
     soucis
    -1.68
     Tienen
    -1.67
     rése
    -1.67
     ciment
    -1.67
     plafon
    -1.63
     etek
    -1.62
    久し
    -1.61
    POSITIVE LOGITS
     and
    2.23
     A
    2.09
     M
    2.08
     so
    1.98
     C
    1.91
     N
    1.91
     L
    1.89
     P
    1.84
     R
    1.81
     S
    1.77
    Activations Density 0.012%

    No Known Activations