Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 52800
    Prev
    Next
    INDEX
    Explanations

    solve new problems or adapt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quilts
    0.47
    ৯
    0.46
    嬂
    0.45
    mens
    0.45
    ndim
    0.44
    tarif
    0.43
    elwv
    0.43
    Ⴊ
    0.43
    ^{*}=
    0.42
    스와
    0.42
    POSITIVE LOGITS
     mė
    0.50
    い
    0.47
    ल्‍
    0.44
    ﻳ
    0.44
     were
    0.43
     kasih
    0.43
     Desert
    0.43
     poised
    0.43
     listrik
    0.43
     ফেরত
    0.43
    Activations Density 0.009%

    No Known Activations