© 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. 128708
    Prev
    Next
    INDEX
    Explanations

    academic papers and articles

    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
    修为
    -1.48
     you
    -1.46
     сообщили
    -1.40
     сыром
    -1.40
    見ると
    -1.40
     творо
    -1.39
    他有
    -1.34
    lawesi
    -1.31
     шокола
    -1.31
     londres
    -1.30
    POSITIVE LOGITS
     dólares
    1.20
     senderismo
    1.20
     българ
    1.18
     promociones
    1.17
    可愛
    1.15
     цвят
    1.15
     galletas
    1.14
    Configurations
    1.13
    Vit
    1.12
     Eigentum
    1.11
    Activations Density 0.004%

    No Known Activations