© 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. 7173
    Prev
    Next
    INDEX
    Explanations

    pointing or waving objects

    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
     Após
    -1.63
     Según
    -1.57
     that
    -1.50
     Apenas
    -1.48
     did
    -1.45
     there
    -1.45
     only
    -1.43
     Lleva
    -1.41
     Años
    -1.40
     Both
    -1.38
    POSITIVE LOGITS
    ns
    1.66
    an
    1.59
    es
    1.57
    sel
    1.48
    </em>
    1.47
    ise
    1.46
    return
    1.46
    on
    1.45
    us
    1.41
    nal
    1.38
    Activations Density 0.019%

    No Known Activations