© 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. 39884
    Prev
    Next
    INDEX
    Explanations

    J followed by i

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

    common surnames

    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
    ’;
    0.49
    aan
    0.48
     is
    0.46
     时
    0.46
     والم
    0.46
    OPLE
    0.46
    EP
    0.45
     مع
    0.45
     medals
    0.45
    dimethyl
    0.45
    POSITIVE LOGITS
    Touched
    0.47
     It
    0.47
     \#
    0.47
    촬
    0.46
     That
    0.45
    Reilly
    0.44
    л
    0.44
     mencapai
    0.44
    il
    0.43
     collectively
    0.43
    Activations Density 0.131%

    No Known Activations