© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66357
    Prev
    Next
    INDEX
    Explanations

    new database query

    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
    很多
    -1.44
    6
    -1.41
    3
    -1.39
    2
    -1.28
    ～　
    -1.23
    7
    -1.22
    只有
    -1.18
    8
    -1.15
     only
    -1.14
    Those
    -1.10
    POSITIVE LOGITS
    umlu
    1.20
    깡
    1.16
    xiaomi
    1.13
     inalámb
    1.13
     homens
    1.11
     extraordinaria
    1.11
     bancos
    1.10
    missile
    1.07
     econó
    1.05
    ducción
    1.04
    Activations Density 0.001%

    No Known Activations