© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 244274
    Prev
    Next
    INDEX
    Explanations

    place names and contexts

    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
     الكل
    0.48
     Snowdon
    0.45
     Pim
    0.45
     Sobre
    0.45
    場合は
    0.44
     По
    0.44
     Gober
    0.44
    .
    0.43
     किसी
    0.43
     que
    0.43
    POSITIVE LOGITS
    రోగ
    0.50
    a
    0.48
    하였습니다
    0.44
    e
    0.44
    мага
    0.44
    منٹ
    0.44
    aerial
    0.43
    නා
    0.43
     เด้อ
    0.43
    aver
    0.42
    Activations Density 0.000%

    No Known Activations