© 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. 1018
    Prev
    Next
    INDEX
    Explanations

    quickly suspicion, lost his, efficient algorithms

    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
     دول
    0.45
    𝗘
    0.44
     ALL
    0.41
     Kwan
    0.41
     EVER
    0.40
     EMEA
    0.40
     malls
    0.40
     আহমেদ
    0.39
     medicines
    0.39
     aisles
    0.39
    POSITIVE LOGITS
    werden
    0.50
    棘
    0.48
    isim
    0.48
    addock
    0.48
    ieft
    0.48
    stool
    0.48
    seudo
    0.47
    effector
    0.46
    riterion
    0.46
    初步
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.