© 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. 112160
    Prev
    Next
    INDEX
    Explanations

    describing something as hilarious

    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
     a
    -2.05
     YOU
    -1.63
    .!
    -1.63
    .?
    -1.63
     correctes
    -1.61
    !.
    -1.52
     geben
    -1.51
    AN
    -1.49
    .&
    -1.46
    .#
    -1.41
    POSITIVE LOGITS
     first
    1.44
     brill
    1.38
     Apt
    1.35
    .
    1.33
    >";
    1.32
    明显的
    1.32
     način
    1.30
     awalnya
    1.30
     apartament
    1.30
    ئم
    1.28
    Activations Density 0.024%

    No Known Activations