© 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-16K
    7. 1105
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis followed by braces

    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_16k_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
    اتج
    1.71
     pho
    1.62
     ong
    1.62
    แม่
    1.60
     Several
    1.59
    รวม
    1.55
     sext
    1.55
     '-
    1.54
    ライ
    1.53
    tank
    1.53
    POSITIVE LOGITS
    pesas
    0.90
     materias
    0.68
    messe
    0.67
    apurna
    0.67
    邂
    0.67
    舉行
    0.66
     premieres
    0.65
    刊行
    0.64
    meleri
    0.64
    cesis
    0.62
    Activations Density 0.268%

    No Known Activations