© 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. 99067
    Prev
    Next
    INDEX
    Explanations

    exhaust systems and components

    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
    According
    -1.49
    although
    -1.48
    While
    -1.47
    also
    -1.47
    褔
    -1.46
    Although
    -1.41
    Not
    -1.39
    However
    -1.38
    甚至
    -1.37
    割と
    -1.35
    POSITIVE LOGITS
     OGSÅ
    1.41
    aww
    1.28
     ulub
    1.27
    undert
    1.26
     Après
    1.24
    ╜
    1.22
    }
    1.22
     quinze
    1.21
     komplette
    1.20
     Cur
    1.19
    Activations Density 0.019%

    No Known Activations