© 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-16K
    7. 264
    Prev
    Next
    INDEX
    Explanations

    Spanish surnames

    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
    Negative Logits
    READER
    0.97
     Mukherjee
    0.92
     Writes
    0.92
    jsk
    0.87
    WG
    0.87
     scrittura
    0.86
     Mikolai
    0.86
     Kasper
    0.85
    ǿ
    0.84
     Pike
    0.84
    POSITIVE LOGITS
     California
    1.43
     Los
    1.35
    California
    1.34
     San
    1.32
     Californians
    1.30
     Calif
    1.27
    Los
    1.26
     Spanish
    1.26
     Mexico
    1.23
     Mexican
    1.23
    Activations Density 4.225%

    No Known Activations