© 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. 34-GEMMASCOPE-RES-131K
    7. 31783
    Prev
    Next
    INDEX
    Explanations

    repeated characters

    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_34/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
    -1.34
     these
    -1.03
     this
    -0.97
     by
    -0.93
     at
    -0.92
     putting
    -0.92
     for
    -0.90
    ではありません
    -0.89
     with
    -0.89
     some
    -0.88
    POSITIVE LOGITS
    AAA
    1.11
    怎么能
    1.06
     огром
    0.99
    rictive
    0.99
    鸰
    0.97
    IEEE
    0.93
    possibly
    0.93
    OOO
    0.92
    viii
    0.92
    OO
    0.92
    Activations Density 0.018%

    No Known Activations