© 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. 2205
    Prev
    Next
    INDEX
    Explanations

    exception as

    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
    maj
    0.92
     Yav
    0.89
    )^{
    0.88
    plit
    0.86
    Model
    0.83
     Analyzer
    0.83
    ισ
    0.83
    政
    0.83
     Model
    0.83
    completion
    0.82
    POSITIVE LOGITS
     demandes
    1.70
    拧
    1.70
    回復
    1.51
    forgot
    1.47
     休
    1.46
     sped
    1.46
    uesday
    1.45
     diaria
    1.45
     reply
    1.44
     speedy
    1.43
    Activations Density 0.080%

    No Known Activations