© 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. 37987
    Prev
    Next
    INDEX
    Explanations

    personal sentiment and foreign words

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

    concepts and abstraction

    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
     filoz
    0.42
     century
    0.40
     needlessly
    0.40
     World
    0.39
    sters
    0.39
     cerebro
    0.39
    ʛ
    0.39
     Century
    0.38
     surfing
    0.38
     searing
    0.38
    POSITIVE LOGITS
     ආ
    0.47
     incarnations
    0.44
    Associate
    0.44
    Again
    0.42
     지금
    0.42
    द्वारे
    0.41
     adesso
    0.41
    Donor
    0.39
    Attendance
    0.39
    ก่อน
    0.38
    Activations Density 0.000%

    No Known Activations