© 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. 19003
    Prev
    Next
    INDEX
    Explanations

    people and their actions

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

    language and people

    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
     و
    0.51
     and
    0.44
     وَ
    0.44
     bụ
    0.43
    可谓
    0.42
     fornisce
    0.42
     circulaire
    0.41
     avait
    0.41
     ۽
    0.40
     تے
    0.40
    POSITIVE LOGITS
     pessoas
    0.58
     people
    0.54
    people
    0.54
     insanlar
    0.54
     люди
    0.53
    pessoas
    0.52
     ಜನರು
    0.51
     ljudi
    0.47
     जनते
    0.47
    निटी
    0.46
    Activations Density 0.000%

    No Known Activations