© 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. 71569
    Prev
    Next
    INDEX
    Explanations

    octal file permissions

    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
    摂
    -1.18
    zieć
    -1.15
    ↵↵
    -1.14
     sources
    -1.09
    <
    -1.08
    
    -1.07
     proiect
    -1.06
     it
    -1.05
     not
    -1.05
     infal
    -1.05
    POSITIVE LOGITS
    皤
    1.25
    Berat
    1.23
    ):
    1.20
     "");
    1.17
     Setelah
    1.15
     doká
    1.10
     Terkait
    1.10
     Rumuni
    1.09
    ໊
    1.09
     ""),
    1.08
    Activations Density 0.129%

    No Known Activations