© 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. 239331
    Prev
    Next
    INDEX
    Explanations

    rats or rodents, which shows, global network, shall mean

    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
    ون
    0.63
    ری
    0.61
    齙
    0.54
    Your
    0.52
    YOUR
    0.51
    重要な
    0.50
    Knowledge
    0.49
    shifts
    0.49
    知識
    0.49
    ຜະລິດຕະພັນ
    0.46
    POSITIVE LOGITS
     źród
    0.51
     imo
    0.47
     marc
    0.47
     tü
    0.47
     想
    0.47
    ški
    0.46
     tutor
    0.46
    ulet
    0.46
     engag
    0.46
     tarif
    0.46
    Activations Density 0.000%

    No Known Activations