© 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. 71332
    Prev
    Next
    INDEX
    Explanations

    was born

    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
     to
    -1.45
     imágen
    -1.44
     participación
    -1.41
     obyvateľov
    -1.41
    着一个
    -1.41
     algunas
    -1.35
    ⧪
    -1.31
    她就
    -1.29
     služby
    -1.27
    着脸
    -1.26
    POSITIVE LOGITS
     our
    1.73
     hes
    1.42
     łóż
    1.41
    :")
    1.40
     his
    1.37
    ляет
    1.35
    Those
    1.30
     Israël
    1.27
     Probably
    1.27
     efektif
    1.26
    Activations Density 0.026%

    No Known Activations