© 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
    2. Gemma-3-270M-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 2074
    Prev
    Next
    INDEX
    Explanations

    image properties or assignments

    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
     '['
    1.85
    ständig
    1.82
     pēc
    1.82
    자는
    1.77
    |$
    1.71
    łada
    1.66
    ześnie
    1.66
    !`
    1.65
    ayati
    1.65
     '</
    1.63
    POSITIVE LOGITS
     効果
    1.14
    But
    1.06
     Reich
    0.99
    OutputDir
    0.97
    效果
    0.95
    Amplitude
    0.92
    but
    0.92
     excès
    0.92
     тем
    0.91
    Accuracy
    0.90
    Activations Density 0.264%

    No Known Activations