© 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. 129772
    Prev
    Next
    INDEX
    Explanations

    letters and numbers following lines

    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
     userDao
    -1.34
     samti
    -1.32
     orale
    -1.30
    着脸
    -1.29
    Usually
    -1.28
    aminan
    -1.19
    🥴
    -1.19
     diego
    -1.19
     signifikan
    -1.16
    Personally
    -1.16
    POSITIVE LOGITS
    asants
    1.27
     venge
    1.15
    <bos>
    1.11
     zmian
    1.05
     Removes
    1.05
     lleno
    1.01
    了许多
    1.01
     groß
    1.01
     focuses
    1.00
     eclectic
    1.00
    Activations Density 0.015%

    No Known Activations