© 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. 127713
    Prev
    Next
    INDEX
    Explanations

    olive oil, Pakistan million

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

    both designed

    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
    مام
    0.49
    輋
    0.49
    inga
    0.45
    feeling
    0.45
    qualified
    0.45
    나
    0.45
     بال
    0.44
    skilled
    0.44
    quito
    0.44
    뱀
    0.44
    POSITIVE LOGITS
     masks
    0.48
     securities
    0.47
     h
    0.46
     STATES
    0.46
     parro
    0.46
     turban
    0.46
     bokeh
    0.45
     Masks
    0.45
     matchups
    0.44
     carb
    0.44
    Activations Density 0.000%

    No Known Activations