© 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. 10870
    Prev
    Next
    INDEX
    Explanations

    wrestling and media personalities

    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
     it
    -1.41
     our
    -1.40
    同学们
    -1.31
     אנחנו
    -1.30
     two
    -1.27
     P
    -1.23
     adored
    -1.23
     It
    -1.22
    얇
    -1.20
     can
    -1.20
    POSITIVE LOGITS
    ṝ
    1.96
     disebutkan
    1.70
    饃
    1.65
     eſſ
    1.63
    謚
    1.61
     procedimiento
    1.55
     eſt
    1.55
    Morfologia
    1.54
     ditawarkan
    1.53
     CHICKEN
    1.51
    Activations Density 0.061%

    No Known Activations