© 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. 18001
    Prev
    Next
    INDEX
    Explanations

    too X than too Y

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

    multi-lingual content

    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
    根據
    0.43
    ctx
    0.42
    pak
    0.41
    PAK
    0.41
    set
    0.40
     맥
    0.40
    ched
    0.40
    ಂಥ
    0.39
    ции
    0.39
     steht
    0.39
    POSITIVE LOGITS
     Laura
    0.46
     ات
    0.44
     Tinker
    0.44
    ጃ
    0.43
     Gloria
    0.43
    лайте
    0.43
     Socialista
    0.43
     روز
    0.42
     Llan
    0.42
     уверен
    0.41
    Activations Density 0.000%

    No Known Activations