© 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. 72218
    Prev
    Next
    INDEX
    Explanations

    FIG. or Category:

    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
     bym
    -1.37
     diras
    -1.23
    عاون
    -1.16
    structing
    -1.16
    !».
    -1.14
    peño
    -1.14
    aufen
    -1.14
     kabát
    -1.12
    ᐈ
    -1.11
     Meksi
    -1.10
    POSITIVE LOGITS
     C
    1.26
    '
    1.21
     durante
    1.19
    ,
    1.18
    3
    1.13
     "
    1.11
    u
    1.11
     D
    1.11
    1
    1.09
     R
    1.09
    Activations Density 0.002%

    No Known Activations