© 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. 111150
    Prev
    Next
    INDEX
    Explanations

    years, numbers, quantities

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

    running code or reports

    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
    មាន
    0.51
    it
    0.49
    Dieser
    0.44
    Right
    0.44
    of
    0.43
    i
    0.43
    디어
    0.43
     Instruction
    0.42
    is
    0.42
     Cartesian
    0.41
    POSITIVE LOGITS
    kube
    0.50
     officielles
    0.50
     नक्की
    0.47
    一台
    0.47
     terj
    0.47
     policewomen
    0.46
     kup
    0.46
    䒨
    0.46
    initpos
    0.44
     വ
    0.44
    Activations Density 0.001%

    No Known Activations