© 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. 64968
    Prev
    Next
    INDEX
    Explanations

    foreign words and names

    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
    <bos>
    -1.57
    ólico
    -1.37
     ciebie
    -1.29
    𐍆
    -1.29
    ChildScrollView
    -1.25
    يادة
    -1.24
    aneity
    -1.23
    . 
    -1.23
    viève
    -1.21
    :'',
    -1.20
    POSITIVE LOGITS
     such
    1.46
    It
    1.42
     given
    1.38
     like
    1.34
    Aiheesta
    1.27
    ないけど
    1.22
    But
    1.20
    にしました
    1.19
     similarly
    1.13
    I
    1.09
    Activations Density 0.003%

    No Known Activations