© 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. 85452
    Prev
    Next
    INDEX
    Explanations

    recirculate, circulate, recycle, return

    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
     zusätzlichen
    -1.52
     Begleitung
    -1.42
    atting
    -1.41
    唷
    -1.41
    ﾎ
    -1.36
    ﾋ
    -1.35
     imprensa
    -1.34
    біль
    -1.27
     fremden
    -1.27
    舒適
    -1.26
    POSITIVE LOGITS
    ",
    1.51
     «
    1.49
    lucht
    1.48
    nocení
    1.35
     -
    1.31
    ୌ
    1.23
     ʻ
    1.23
    AllowAnonymous
    1.23
     américa
    1.22
    withCredentials
    1.22
    Activations Density 0.027%

    No Known Activations