© 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. 39911
    Prev
    Next
    INDEX
    Explanations

    oh followed by punctuation or filler

    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
    S
    -2.06
     These
    -2.02
     estos
    -1.93
     of
    -1.91
    これらの
    -1.89
    up
    -1.82
     is
    -1.79
    these
    -1.76
     queste
    -1.76
    这些
    -1.73
    POSITIVE LOGITS
     tremend
    1.58
    Etimo
    1.57
    rý
    1.55
     ...,
    1.53
    czeń
    1.52
    rões
    1.52
    otide
    1.52
    クター
    1.52
     nieve
    1.49
     infal
    1.48
    Activations Density 0.016%

    No Known Activations