© 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. 238090
    Prev
    Next
    INDEX
    Explanations

    common word pairings

    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
    zą
    0.51
     हित
    0.51
    ी
    0.50
    री
    0.50
     ကျွန်
    0.50
     maksymal
    0.48
    زمین
    0.48
    硣
    0.47
    ก
    0.46
     मीरा
    0.46
    POSITIVE LOGITS
    lllll
    0.46
    clk
    0.44
    usas
    0.43
    \.
    0.43
    hhhh
    0.42
    recent
    0.41
     BJ
    0.41
     carinatis
    0.40
    aquin
    0.40
    uxx
    0.40
    Activations Density 0.001%

    No Known Activations