© 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. 71437
    Prev
    Next
    INDEX
    Explanations

    Nicholas followed by a surname

    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
    u
    -2.89
    i
    -2.33
    on
    -2.22
    \
    -2.20
     When
    -2.20
     The
    -2.11
    嚳
    -2.06
    ﹆
    -2.03
    er
    -2.02
     Have
    -2.00
    POSITIVE LOGITS
    趼
    3.23
    ࿚
    2.63
    蹀
    2.52
    袛
    2.34
    鸶
    2.31
    .“
    2.25
    
    2.23
    Etc
    2.22
    “,
    2.19
    “)
    2.19
    Activations Density 0.005%

    No Known Activations