© 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. 67575
    Prev
    Next
    INDEX
    Explanations

    apple macintosh computers

    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
    in
    -3.86
    ↵
    -3.59
    on
    -3.56
    I
    -3.48
    an
    -3.44
     —
    -3.41
    .
    -3.38
    0
    -3.25
     
    -3.00
    or
    -2.92
    POSITIVE LOGITS
    昻
    3.81
    튿
    3.67
    漚
    3.58
    ྄
    3.53
    ଝ
    3.52
    ⬯
    3.41
    genodigd
    3.41
    횃
    3.34
    樒
    3.31
    titial
    3.27
    Activations Density 0.002%

    No Known Activations