© 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. 14197
    Prev
    Next
    INDEX
    Explanations

    code snippets and foreign words

    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
     just
    -1.43
     in
    -1.43
    The
    -1.39
     all
    -1.37
    委員會
    -1.28
     new
    -1.26
     website
    -1.26
     my
    -1.25
     even
    -1.25
    子は
    -1.24
    POSITIVE LOGITS
    きち
    1.45
    為に
    1.40
    Ꮞ
    1.39
     queste
    1.34
    ḿ
    1.32
     phénomènes
    1.27
    seitigen
    1.23
    Missi
    1.23
    pulseira
    1.23
    íd
    1.19
    Activations Density 0.001%

    No Known Activations