© 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. 10-GEMMASCOPE-RES-131K
    7. 68270
    Prev
    Next
    INDEX
    Explanations

    knowing, finding, or seeing something

    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_10/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
     that
    -2.02
     it
    -1.43
     tenté
    -1.41
     lavet
    -1.38
    hhhhh
    -1.37
    kkkk
    -1.36
    ::::::::::::::::
    -1.35
    豋
    -1.35
     feitos
    -1.34
    kkk
    -1.31
    POSITIVE LOGITS
     a
    2.50
    <bos>
    1.41
     Vorgang
    1.33
     lots
    1.28
    的人物
    1.27
     Glaube
    1.27
     Unterschied
    1.19
     ahora
    1.19
     glauben
    1.19
     Gefähr
    1.18
    Activations Density 0.031%

    No Known Activations