© 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. 73161
    Prev
    Next
    INDEX
    Explanations

    again or repetition

    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
     this
    -1.49
     to
    -1.47
     during
    -1.44
     which
    -1.37
     because
    -1.32
     before
    -1.31
     that
    -1.30
     as
    -1.30
     if
    -1.30
     could
    -1.29
    POSITIVE LOGITS
    Again
    1.45
    again
    1.39
     novamente
    1.34
    再一次
    1.23
     again
    1.23
     actuellement
    1.17
     опять
    1.15
    wasn
    1.15
     снова
    1.14
     remé
    1.13
    Activations Density 0.027%

    No Known Activations