© 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. 246044
    Prev
    Next
    INDEX
    Explanations

    pre-analytical care and recovery

    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
    *.
    0.46
    *:
    0.46
    ped
    0.46
    stan
    0.45
    esa
    0.44
    isati
    0.44
    ata
    0.44
    :");
    0.44
    CLUDING
    0.44
    SOCK
    0.43
    POSITIVE LOGITS
     from
    0.51
    ล
    0.47
    ม
    0.46
    گن
    0.45
     entre
    0.45
     từ
    0.45
     $(".
    0.44
     ล้าน
    0.44
     reale
    0.43
     From
    0.43
    Activations Density 0.000%

    No Known Activations