© 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. 150321
    Prev
    Next
    INDEX
    Explanations

    reflect major, click on, wasted on

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

    They are their

    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
     postulated
    0.52
    l
    0.52
     Пар
    0.52
    ಶ
    0.51
    t
    0.49
     Pampl
    0.49
     населення
    0.48
     ludzi
    0.47
     morphisms
    0.47
     Ríos
    0.47
    POSITIVE LOGITS
     quang
    0.45
    Categor
    0.43
     abd
    0.43
    abetic
    0.43
     auc
    0.42
    กาย
    0.41
    ilipp
    0.40
    aleb
    0.40
    岩
    0.40
    坚
    0.40
    Activations Density 0.000%

    No Known Activations