© 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. 4193
    Prev
    Next
    INDEX
    Explanations

    which

    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
     aspect
    1.83
    emate
    1.79
    部は
    1.75
    izability
    1.75
    できなかった
    1.74
    ized
    1.72
    들은
    1.70
    =="
    1.68
    ization
    1.68
    ability
    1.67
    POSITIVE LOGITS
    which
    1.31
    ซึ่ง
    1.17
     ซึ่ง
    1.14
     wich
    1.14
     koja
    1.13
     WHICH
    1.10
     which
    1.08
     cuyo
    1.03
     což
    0.99
     cujo
    0.97
    Activations Density 0.150%

    No Known Activations