© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 196546
    Prev
    Next
    INDEX
    Explanations

    heat

    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_all/layer_41_width_262k_l0_big
    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
    ن
    0.44
    اران
    0.39
    与之
    0.39
    貓
    0.38
     takers
    0.37
    呲
    0.37
    Lauren
    0.37
    No
    0.36
     underwater
    0.36
     ওকে
    0.36
    POSITIVE LOGITS
    クトル
    0.45
     воздействия
    0.44
     컬
    0.44
     ҳ
    0.44
    igroup
    0.43
    ique
    0.42
     сохранения
    0.41
    obl
    0.40
    wght
    0.40
     документа
    0.39
    Activations Density 0.231%

    No Known Activations