© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 208081
    Prev
    Next
    INDEX
    Explanations

    from the

    np_acts-logits-general · gemini-2.5-flash-lite

    Assessing strengths and capacity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    (
    0.54
     It
    0.51
    見
    0.50
    It
    0.47
    在
    0.47
    （
    0.46
     средство
    0.46
    一
    0.45
     kẻ
    0.45
    *)
    0.44
    POSITIVE LOGITS
    getTransforms
    0.54
    薈
    0.54
     автофо
    0.54
    abolism
    0.52
    स्पून
    0.51
    unków
    0.50
     archetype
    0.50
     LMFBR
    0.50
    AudioAsset
    0.50
     interdiscipl
    0.49
    Activations Density 0.000%

    No Known Activations