© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19763
    Prev
    Next
    INDEX
    Explanations

    Europe, chess, code, currency

    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_262k_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
    ,
    0.43
    0.43
     parchment
    0.43
     vocals
    0.42
     scarves
    0.41
     soud
    0.40
     speech
    0.40
     reading
    0.40
     و
    0.39
     confe
    0.39
    POSITIVE LOGITS
    Მ
    0.50
    criar
    0.44
    сама
    0.43
    Lista
    0.42
    )}_
    0.41
     создавать
    0.41
    ambiental
    0.41
    buatan
    0.40
    Компания
    0.40
    sistema
    0.40
    Activations Density 0.001%

    No Known Activations