© 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. 240191
    Prev
    Next
    INDEX
    Explanations

    hives, pipes, music, Medicaid, hours

    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
    晤
    0.51
     Queer
    0.50
    рг
    0.47
    рави
    0.46
    niają
    0.43
    นด์
    0.43
    াজিক
    0.43
    hObject
    0.42
    nesset
    0.41
     ([[
    0.41
    POSITIVE LOGITS
     faite
    0.57
     envoyer
    0.52
    ASY
    0.48
     tester
    0.47
     compliance
    0.47
     쓰는
    0.46
    anne
    0.46
     checks
    0.45
     malos
    0.45
    ang
    0.45
    Activations Density 0.001%

    No Known Activations