© 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. 34-GEMMASCOPE-RES-131K
    7. 31335
    Prev
    Next
    INDEX
    Explanations

    BMW models and series

    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_34/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
     dump
    -0.74
    tillation
    -0.69
     portare
    -0.68
    óngase
    -0.68
     Τα
    -0.67
     спокойно
    -0.66
     Sext
    -0.66
    ellar
    -0.66
    getOr
    -0.65
    UFF
    -0.65
    POSITIVE LOGITS
    Tribal
    0.84
    сар
    0.82
     cubanos
    0.79
     troca
    0.75
    BMW
    0.75
     Competition
    0.75
    sser
    0.74
    oracle
    0.74
    pital
    0.74
    וֹ
    0.74
    Activations Density 0.021%

    No Known Activations