© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111484
    Prev
    Next
    INDEX
    Explanations

    quoted phrases

    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
     you
    -1.66
     infatti
    -1.63
     here
    -1.55
    4
    -1.42
    this
    -1.41
     ktoś
    -1.40
    於是
    -1.39
    astian
    -1.38
    真的好
    -1.38
     statunitense
    -1.37
    POSITIVE LOGITS
     from
    1.70
     an
    1.57
     pēc
    1.51
    maxsize
    1.41
    “.
    1.38
    ▾
    1.37
     one
    1.34
     as
    1.34
    ৫
    1.34
    []):
    1.32
    Activations Density 0.051%

    No Known Activations