© 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. 14693
    Prev
    Next
    INDEX
    Explanations

    question starter words

    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
     både
    -1.95
     mété
    -1.78
    鉿
    -1.75
    侂
    -1.74
    >>>>>>
    -1.69
     rembourse
    -1.66
     ビキニ
    -1.62
     conhece
    -1.57
     bénéfices
    -1.56
     UserDao
    -1.55
    POSITIVE LOGITS
     which
    1.87
     of
    1.76
     from
    1.61
     no
    1.58
     all
    1.55
     will
    1.48
     during
    1.48
     events
    1.48
     out
    1.46
     like
    1.45
    Activations Density 0.119%

    No Known Activations