© 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. 99040
    Prev
    Next
    INDEX
    Explanations

    apologies and inconvenience

    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
     a
    -1.65
    摑
    -1.33
     found
    -1.32
     wales
    -1.27
     two
    -1.24
     Interestingly
    -1.20
     using
    -1.18
     Compared
    -1.17
    jścia
    -1.16
    正解
    -1.15
    POSITIVE LOGITS
    {~
    1.53
    THEY
    1.48
     keine
    1.48
    ldots
    1.47
     môžete
    1.42
     tých
    1.42
     niektor
    1.39
    šek
    1.36
    なども
    1.34
    8
    1.34
    Activations Density 0.015%

    No Known Activations