© 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. 112812
    Prev
    Next
    INDEX
    Explanations

    describing items or concepts

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

    past tense or discontinued

    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
    Not in Any Lists

    No Comments

    Negative Logits
     trauer
    0.48
    禇
    0.47
    傈
    0.46
    truth
    0.46
    鵃
    0.45
     futbol
    0.45
     आसमान
    0.45
     हूँ
    0.44
    ართ
    0.44
    𝗯
    0.44
    POSITIVE LOGITS
     wrongly
    0.52
    もあった
    0.49
     had
    0.49
     discontinued
    0.46
    しかった
    0.43
     deprived
    0.43
     unsuccessfully
    0.43
     sui
    0.42
     prevailed
    0.42
    ាញ
    0.41
    Activations Density 0.001%

    No Known Activations