© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68023
    Prev
    Next
    INDEX
    Explanations

    attribution or authorship

    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_22/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
     in
    -1.96
    子は
    -1.86
     all
    -1.59
     with
    -1.53
     by
    -1.48
     for
    -1.48
     on
    -1.39
    を
    -1.38
     without
    -1.36
     have
    -1.34
    POSITIVE LOGITS
    為に
    1.57
    튿
    1.52
     aanzien
    1.38
    場所で
    1.34
    きち
    1.31
    ところです
    1.29
     envoyer
    1.28
    ままで
    1.25
     avven
    1.23
    踭
    1.23
    Activations Density 0.000%

    No Known Activations