© 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. 1440
    Prev
    Next
    INDEX
    Explanations

    YouTube video IDs

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

    youtube playlist urls

    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
     ferrugineux
    0.60
    ONEDB
    0.49
     messageFields
    0.48
     thalassemia
    0.48
    Aslamualaikum
    0.46
     Hydrochloride
    0.46
    癀
    0.46
    SpringMVCProject
    0.46
    㓞
    0.46
     graders
    0.45
    POSITIVE LOGITS
    y
    0.65
    z
    0.64
    it
    0.61
    we
    0.61
    i
    0.61
    e
    0.60
     P
    0.59
    w
    0.59
    en
    0.57
    or
    0.57
    Activations Density 0.000%

    No Known Activations