© 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. 206400
    Prev
    Next
    INDEX
    Explanations

    expensive, personal, shepherd, goals

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

    together was year word route

    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
    ch
    0.46
    Pharmacy
    0.44
    a
    0.44
    കോ
    0.44
    vent
    0.43
    variant
    0.42
    o
    0.42
    ar
    0.41
    v
    0.41
    ic
    0.41
    POSITIVE LOGITS
     사용하는
    0.53
     매우
    0.52
     palav
    0.51
     slučaj
    0.51
     veoma
    0.51
    ще
    0.50
    gateTime
    0.49
     poes
    0.49
    れない
    0.48
    다른
    0.48
    Activations Density 0.000%

    No Known Activations