© 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. 58886
    Prev
    Next
    INDEX
    Explanations

    predicts positive intense descriptions

    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
     and
    -2.63
     because
    -2.47
     that
    -2.41
     one
    -2.34
     should
    -2.28
     before
    -2.23
     as
    -2.20
     any
    -2.17
     if
    -2.16
     some
    -2.09
    POSITIVE LOGITS
     ridiculously
    2.19
     insanely
    2.13
     unbelievably
    2.09
     deliciously
    2.05
     wonderfully
    2.02
     delightfully
    2.02
     soooo
    2.00
     renowned
    1.99
     magnific
    1.98
     jn
    1.98
    Activations Density 0.165%

    No Known Activations