© 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. 39663
    Prev
    Next
    INDEX
    Explanations

    library imports and model declarations

    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
     into
    -1.16
    不出
    -1.13
    楽しんで
    -1.11
     każdy
    -1.08
     inside
    -1.05
     they
    -1.05
     our
    -1.05
    遊んで
    -1.03
     towards
    -1.03
    nivea
    -1.02
    POSITIVE LOGITS
     土産
    1.36
     dår
    1.31
     rire
    1.23
     porcelana
    1.22
     camiset
    1.21
    LÄ
    1.20
     strå
    1.19
     problemer
    1.18
    Recept
    1.18
    Jadi
    1.17
    Activations Density 0.018%

    No Known Activations