© 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. 30333
    Prev
    Next
    INDEX
    Explanations

    is a way

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

    included explanations, visuals, considerations

    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
    意大利
    0.55
     ଏ
    0.55
    纽约
    0.55
    Selling
    0.52
    판매
    0.52
     decks
    0.50
    ニューヨーク
    0.50
    檜
    0.49
    Termination
    0.49
    賣
    0.49
    POSITIVE LOGITS
     (*
    0.51
     descriptor
    0.45
     Parser
    0.45
     (**
    0.43
     (++
    0.43
     zum
    0.43
     C
    0.43
     vrou
    0.42
     problemat
    0.41
     fol
    0.41
    Activations Density 0.000%

    No Known Activations