© 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. 22-GEMMASCOPE-RES-131K
    7. 72101
    Prev
    Next
    INDEX
    Explanations

    more repetition specific details

    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
     their
    -2.53
     on
    -2.31
     at
    -2.23
     only
    -2.17
     with
    -2.14
     what
    -2.13
     as
    -2.11
     an
    -2.11
     first
    -2.09
     both
    -2.08
    POSITIVE LOGITS
     Dinas
    1.88
     deliciously
    1.77
     delightfully
    1.63
     horrend
    1.55
     accentu
    1.53
     luscious
    1.52
     horrid
    1.52
     magnific
    1.49
     unbelievably
    1.49
     intrigu
    1.48
    Activations Density 0.127%

    No Known Activations