© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2745
    Prev
    Next
    INDEX
    Explanations

    user questions or instructions

    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
    吁
    1.52
     tight
    1.50
     déi
    1.41
     him
    1.39
    解决了
    1.38
     tees
    1.37
    Newswire
    1.34
    ments
    1.33
    ويم
    1.33
     CHARSET
    1.33
    POSITIVE LOGITS
    NUMX
    3.26
    7
    3.07
    oxo
    2.92
    rinsic
    2.90
    4
    2.88
    8
    2.86
    6
    2.82
    5
    2.79
    3
    2.73
    ٧
    2.54
    Activations Density 0.176%

    No Known Activations