© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4832
    Prev
    Next
    INDEX
    Explanations

    Charles de

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     trộn
    1.60
    ᅭ
    1.51
     hỗn
    1.50
    ungsk
    1.46
    ujourd
    1.46
    itekt
    1.44
     diente
    1.44
     pás
    1.43
    єкт
    1.41
     zelfs
    1.40
    POSITIVE LOGITS
    aime
    1.28
    izens
    1.28
    ™
    1.25
    iset
    1.22
    棪
    1.14
    敝
    1.12
    alcool
    1.12
     systematically
    1.12
     yake
    1.10
    自身的
    1.09
    Activations Density 0.001%

    No Known Activations