© 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. 66477
    Prev
    Next
    INDEX
    Explanations

    midpoints and endpoints

    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
    ↵↵
    -1.95
    __((
    -1.70
    …”
    -1.68
    </h4>
    -1.59
    ity
    -1.54
     mantequilla
    -1.52
    勦
    -1.51
    垆
    -1.49
    …)
    -1.48
    ”
    -1.48
    POSITIVE LOGITS
     of
    2.17
     then
    1.66
     our
    1.59
    呗
    1.58
     between
    1.56
     likewise
    1.56
     prøve
    1.56
     proget
    1.52
     méxico
    1.50
     tilby
    1.48
    Activations Density 0.007%

    No Known Activations