© 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. 156186
    Prev
    Next
    INDEX
    Explanations

    location based

    np_acts-logits-general · gemini-2.5-flash-lite

    render, baked, mf, from

    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
    Recorder
    0.48
    ረ
    0.47
    кие
    0.46
     внутреннего
    0.46
    Mens
    0.45
    Points
    0.44
    ें
    0.44
    杲
    0.44
    errorMessage
    0.43
    рные
    0.43
    POSITIVE LOGITS
     bernama
    0.46
     someplace
    0.46
    ように
    0.45
     غادي
    0.43
     특별
    0.43
     trong
    0.43
     hangi
    0.43
     isn
    0.42
     labeled
    0.42
     berjudul
    0.42
    Activations Density 0.001%

    No Known Activations