© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 33388
    Prev
    Next
    INDEX
    Explanations

    loading data from files

    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
     a
    -1.43
     |
    -1.39
    0
    -1.29
     value
    -1.28
     to
    -1.24
    _
    -1.24
     eventually
    -1.20
     only
    -1.17
     “
    -1.17
     y
    -1.17
    POSITIVE LOGITS
     from
    1.45
    eload
    1.41
     refroid
    1.35
     corriger
    1.29
    ᯅ
    1.16
    yyv
    1.13
     scherm
    1.13
     réjou
    1.12
     nettsted
    1.12
     récomp
    1.12
    Activations Density 0.008%

    No Known Activations