© 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. 110748
    Prev
    Next
    INDEX
    Explanations

    sellingsellingsellingpropertysellingsellingsellingsellingsellingselling

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

    alternatives, policy, religious beliefs

    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
    ch
    0.55
    conference
    0.55
    icto
    0.49
    iere
    0.49
    aries
    0.49
    ឡ
    0.48
    ole
    0.47
    PO
    0.47
    ds
    0.47
    loy
    0.47
    POSITIVE LOGITS
     সাত
    0.54
    ;(
    0.49
     кілька
    0.48
     восем
    0.47
     Duss
    0.46
     powied
    0.46
    เนื่อง
    0.45
     Dinosaur
    0.45
     Lâm
    0.45
     দুই
    0.45
    Activations Density 0.000%

    No Known Activations