© 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. 155482
    Prev
    Next
    INDEX
    Explanations

    services, requirements, remaining

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

    varies linearly

    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
     Burke
    0.56
    喜
    0.50
     Hesse
    0.50
     Meir
    0.47
     AUTO
    0.46
     Abdel
    0.46
     Eric
    0.46
     Annette
    0.46
    به
    0.45
    Cache
    0.45
    POSITIVE LOGITS
    phus
    0.48
    勮
    0.48
    supp
    0.48
    pendicular
    0.47
    ウザ
    0.46
    scatter
    0.46
    τσι
    0.45
     corticoster
    0.45
    secondary
    0.45
    erunner
    0.44
    Activations Density 0.000%

    No Known Activations