© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40817
    Prev
    Next
    INDEX
    Explanations

    import or require modules

    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
     your
    -1.67
     just
    -1.67
     What
    -1.63
     what
    -1.61
     everyone
    -1.51
     why
    -1.47
     Why
    -1.46
    f
    -1.40
     Here
    -1.40
     but
    -1.39
    POSITIVE LOGITS
     チラ
    1.60
    媜
    1.60
    eine
    1.50
    芈
    1.49
     razu
    1.49
    馋
    1.46
     kwi
    1.43
     mavi
    1.41
     komis
    1.41
    ifikant
    1.38
    Activations Density 0.022%

    No Known Activations