© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 5202
    Prev
    Next
    INDEX
    Explanations

    controller driver

    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
    Negative Logits
    瘍
    1.64
    缝
    1.57
    мец
    1.57
    cuno
    1.54
     رحمه
    1.53
     усі
    1.52
    времен
    1.51
    یث
    1.50
    数为
    1.50
    표
    1.49
    POSITIVE LOGITS
    houses
    2.27
    lifting
    2.24
    tableFuture
    2.07
    house
    2.03
     mẽ
    1.93
     wield
    1.90
    𝖓
    1.86
    resonant
    1.84
     CRUD
    1.80
     radiated
    1.79
    Activations Density 0.064%

    No Known Activations