© 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. 12194
    Prev
    Next
    INDEX
    Explanations

    describes possessions

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

    agrivoltaics, NAND, stool, IT, миндалины, Hack, human

    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
     ذریع
    0.53
    .*
    0.51
     کی۔
    0.49
    *.
    0.48
    ებისა
    0.47
    4
    0.47
     گئی۔
    0.46
    3
    0.46
    .\
    0.45
     thiab
    0.44
    POSITIVE LOGITS
    物は
    0.64
     has
    0.57
    ものは
    0.57
     provides
    0.55
     does
    0.54
     possesses
    0.54
     έχει
    0.53
     is
    0.52
     имеет
    0.51
     boasts
    0.51
    Activations Density 0.113%

    No Known Activations