© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 220936
    Prev
    Next
    INDEX
    Explanations

    policy or insurance claim

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

    database connection, pointing generally, capture low

    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
    Negative Logits
     llevará
    0.49
    橦
    0.44
     –,
    0.43
     OFFER
    0.43
     morti
    0.43
    fone
    0.43
     ampliar
    0.43
     acolo
    0.42
    COTT
    0.42
    বেলা
    0.42
    POSITIVE LOGITS
    ழ்க
    0.48
    aris
    0.47
     standardised
    0.47
    ழுத
    0.46
    u
    0.45
    urin
    0.42
     第三
    0.42
     ธ
    0.42
    الا
    0.42
     opdracht
    0.41
    Activations Density 0.001%

    No Known Activations