© 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. 55744
    Prev
    Next
    INDEX
    Explanations

    employer offer

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

    suggest topics

    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
     الجميع
    0.45
    買い
    0.44
    畚
    0.43
     বৎস
    0.43
    Ꮭ
    0.42
     మహ
    0.42
    Ꮟ
    0.41
    қу
    0.41
     család
    0.41
    ාර
    0.41
    POSITIVE LOGITS
    ugu
    0.52
     ISC
    0.51
    Ur
    0.51
    ut
    0.49
     in
    0.48
    ft
    0.48
    wik
    0.48
    It
    0.47
     Suffering
    0.47
     Neph
    0.47
    Activations Density 0.000%

    No Known Activations