© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27496
    Prev
    Next
    INDEX
    Explanations

    data abstraction and review

    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
     with
    -1.46
     but
    -1.40
     or
    -1.39
    羸
    -1.28
     before
    -1.27
     one
    -1.19
    外人
    -1.17
     at
    -1.16
     nebo
    -1.13
     stylish
    -1.11
    POSITIVE LOGITS
    ּוֹ
    1.19
     bisogna
    1.19
     kombat
    1.15
     satria
    1.13
     daewoo
    1.13
     alcuni
    1.13
     criteria
    1.13
    のではないか
    1.13
    のではない
    1.13
     विश्लेषण
    1.10
    Activations Density 0.139%

    No Known Activations