© 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. 66996
    Prev
    Next
    INDEX
    Explanations

    man

    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
     reports
    -1.83
     luy
    -1.75
     Mereka
    -1.74
     ftate
    -1.70
     eigenes
    -1.66
     rangs
    -1.66
     fhort
    -1.63
    Femin
    -1.62
    ÑO
    -1.60
     damskie
    -1.59
    POSITIVE LOGITS
    .
    1.86
     While
    1.85
     According
    1.84
     Why
    1.69
    2
    1.66
    It
    1.63
    所有
    1.63
    先是
    1.62
     (
    1.61
     Allowing
    1.61
    Activations Density 0.011%

    No Known Activations