© 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. 137350
    Prev
    Next
    INDEX
    Explanations

    silver coin sales and value

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

    focused on growing grasses

    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
    માં
    0.50
     Ευ
    0.46
    涫
    0.46
     боя
    0.45
     Entry
    0.45
     солнца
    0.44
    b
    0.44
    μο
    0.44
    olio
    0.44
     বালা
    0.44
    POSITIVE LOGITS
     sane
    0.50
     できる
    0.47
     prejud
    0.44
     pronounce
    0.44
    瀰
    0.44
     condemns
    0.43
    РС
    0.43
     rational
    0.43
     justifications
    0.43
    وري
    0.42
    Activations Density 0.001%

    No Known Activations