© 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. 84873
    Prev
    Next
    INDEX
    Explanations

    stewardship and being steeped

    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
    ي
    -3.03
    饜
    -2.98
    鼙
    -2.47
    梣
    -2.44
    說
    -2.44
    鯓
    -2.42
    ר
    -2.41
    ︕
    -2.39
    ⎚
    -2.38
    "}}>
    -2.33
    POSITIVE LOGITS
     .
    3.13
     of
    3.03
     nueve
    2.34
    a
    2.34
    vantaged
    2.31
    ERS
    2.28
     awful
    2.27
    ists
    2.23
     
    2.23
    s
    2.22
    Activations Density 0.001%

    No Known Activations