© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70063
    Prev
    Next
    INDEX
    Explanations

    relative positioning

    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
    -1.83
     from
    -1.58
     to
    -1.56
     suele
    -1.54
     cuya
    -1.48
     reconocida
    -1.44
     �
    -1.39
     cuja
    -1.37
     is
    -1.35
     will
    -1.34
    POSITIVE LOGITS
    και
    1.62
    enseignements
    1.58
    櫪
    1.53
     pracę
    1.49
    出發
    1.48
     traductions
    1.48
    萏
    1.46
    かなり
    1.46
    あなた
    1.45
    eluarkan
    1.45
    Activations Density 0.001%

    No Known Activations