© 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. 139903
    Prev
    Next
    INDEX
    Explanations

    after proper noun

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

    FROM followed by entity names

    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
    estation
    0.56
    worth
    0.51
    embrance
    0.48
     ނ
    0.48
    acuse
    0.47
    isteren
    0.47
    itent
    0.46
    ogan
    0.46
    inak
    0.46
    nehm
    0.45
    POSITIVE LOGITS
     reali
    0.49
    Hare
    0.48
     rive
    0.47
     AVE
    0.45
    锉
    0.45
    苍
    0.44
     찍
    0.44
     IRE
    0.43
     iniciando
    0.43
    河
    0.42
    Activations Density 0.001%

    No Known Activations