© 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. 7258
    Prev
    Next
    INDEX
    Explanations

    numbers, sections, group

    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
     verschiedene
    -1.37
    ต่างๆ
    -1.27
    different
    -1.21
    哢
    -1.18
    你先
    -1.18
    Abbildung
    -1.17
    時半
    -1.17
     diferentes
    -1.16
     verschillende
    -1.16
     silky
    -1.15
    POSITIVE LOGITS
     who
    2.03
    ."
    1.54
     whose
    1.49
     veľa
    1.48
     sababu
    1.32
     with
    1.27
     and
    1.19
     môžu
    1.18
     spôso
    1.16
     rých
    1.15
    Activations Density 0.115%

    No Known Activations