© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 240515
    Prev
    Next
    INDEX
    Explanations

    particular item, politics and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uig
    0.54
    贯彻
    0.47
     beeh
    0.45
     fonds
    0.45
    "=>$
    0.45
     જણાવ્યું
    0.44
    百家乐
    0.44
    SpecID
    0.44
     значи
    0.44
    "};
    0.44
    POSITIVE LOGITS
    נ
    0.50
    ρε
    0.47
    нется
    0.47
    ਹ
    0.46
    पेड
    0.46
    posite
    0.45
    ിലാ
    0.45
    統
    0.44
     ducts
    0.44
    隨
    0.44
    Activations Density 0.000%

    No Known Activations