© 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. 217210
    Prev
    Next
    INDEX
    Explanations

    listing items after a noun

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

    hotel refund advice

    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
     然而
    0.44
    াপন্ন
    0.43
    হয়
    0.43
    之地
    0.42
    SalesRep
    0.42
    alyse
    0.42
    崗
    0.42
    ྰ
    0.42
     कानून
    0.42
     হারা
    0.41
    POSITIVE LOGITS
     nieuw
    0.47
     punten
    0.46
     květ
    0.45
    zás
    0.45
     nieuwe
    0.44
     zeer
    0.44
    CONCEPT
    0.43
     zeggen
    0.43
    (
    0.43
     мі
    0.43
    Activations Density 0.000%

    No Known Activations