© 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. 119668
    Prev
    Next
    INDEX
    Explanations

    northeasterly easterly

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

    lists of reasons or explanations

    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
    Ғ
    0.58
    Für
    0.57
     پیغمبر
    0.52
    க்தி
    0.52
     funzionalità
    0.52
    ாந்து
    0.52
    MiddleLine
    0.52
     fratello
    0.51
    રિક
    0.51
    ீரி
    0.50
    POSITIVE LOGITS
     OECD
    0.54
    c
    0.51
     lawful
    0.48
     escrow
    0.47
     correspondingly
    0.45
    pg
    0.45
    ):
    0.45
    pays
    0.44
    =
    0.44
     শহরের
    0.43
    Activations Density 0.002%

    No Known Activations