© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3659
    Prev
    Next
    INDEX
    Explanations

    explanation, benefits, schedule, lambda

    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
    7
    0.63
    inois
    0.51
    のだろう
    0.50
    rinsic
    0.50
    輸入品
    0.48
    不管是
    0.47
    uminous
    0.46
    6
    0.46
    ctors
    0.43
    矜
    0.43
    POSITIVE LOGITS
     orator
    1.64
    s
    1.59
     Strategy
    1.59
     parades
    1.52
    ات
    1.51
     病
    1.50
    ย
    1.50
    م
    1.48
     manoe
    1.48
    sizer
    1.47
    Activations Density 0.003%

    No Known Activations