© 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. 73175
    Prev
    Next
    INDEX
    Explanations

    people and names followed by verbs

    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
     jde
    -1.58
     also
    -1.52
    ࿆
    -1.41
    +}\
    -1.39
     también
    -1.36
    ଃ
    -1.35
     også
    -1.34
     gustaMe
    -1.34
     Hän
    -1.33
     nakalista
    -1.33
    POSITIVE LOGITS
    l
    1.73
    u
    1.72
     I
    1.59
    k
    1.54
    5
    1.52
    这么多
    1.49
    p
    1.46
    n
    1.45
    0
    1.45
    is
    1.43
    Activations Density 0.053%

    No Known Activations