© 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. 69082
    Prev
    Next
    INDEX
    Explanations

    affordable rooms, law, hosting services

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

    congruence, equivalence, or "same"

    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
    そして
    0.44
    ᱫ
    0.44
    Ralph
    0.44
    嵃
    0.44
    ຈ
    0.44
     résumé
    0.43
    挑戰
    0.43
    ယ
    0.43
    。”
    0.43
    ಿರ
    0.43
    POSITIVE LOGITS
     أبر
    0.49
    ps
    0.48
    mets
    0.48
    mi
    0.47
    cluster
    0.47
    activated
    0.47
    ins
    0.46
     يحتوي
    0.46
    ulen
    0.46
    uw
    0.46
    Activations Density 0.000%

    No Known Activations