© 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. 26318
    Prev
    Next
    INDEX
    Explanations

    he, she, his, her

    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
     offiziell
    -1.14
     grundsätzlich
    -1.12
     alltid
    -1.08
     föränd
    -1.08
    怎么可能
    -1.04
     krwi
    -1.04
     gänzlich
    -1.02
     meistens
    -0.99
     bree
    -0.99
     새로운
    -0.98
    POSITIVE LOGITS
     varias
    1.20
     all
    1.16
    ！(
    1.11
     بسیار
    1.10
     gaben
    1.07
     if
    1.06
     ALL
    1.05
    alties
    1.05
    urlencoded
    1.02
    ？？？
    1.02
    Activations Density 0.035%

    No Known Activations