© 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. 244805
    Prev
    Next
    INDEX
    Explanations

    factors could cause

    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
    瘁
    0.48
     mivel
    0.47
     campagnes
    0.45
    يد
    0.45
    тон
    0.44
    所有的
    0.44
     SERVICE
    0.43
    ชีพ
    0.43
    支
    0.43
    يف
    0.42
    POSITIVE LOGITS
    lc
    0.48
     random
    0.47
     handed
    0.46
    opre
    0.45
     contradictory
    0.45
    othes
    0.45
     enabling
    0.45
    bridge
    0.44
     FAQs
    0.44
     handover
    0.44
    Activations Density 0.001%

    No Known Activations