© 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. 3366
    Prev
    Next
    INDEX
    Explanations

    driven insights

    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
     embarrassment
    1.66
    年は
    1.66
    愆
    1.64
     festivities
    1.61
     erros
    1.61
    倹
    1.61
     conservatism
    1.58
    瞓
    1.57
    بعض
    1.55
    是个
    1.51
    POSITIVE LOGITS
     locate
    1.11
    依次
    1.09
     teleport
    1.07
     vox
    1.07
     sweeping
    1.07
     توز
    1.06
     inund
    1.05
     tirelessly
    1.01
     distribute
    1.01
    arak
    1.01
    Activations Density 0.117%

    No Known Activations