© 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. 62544
    Prev
    Next
    INDEX
    Explanations

    shell commands

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

    bash commands

    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
     preso
    0.46
     accumulation
    0.44
     tiling
    0.43
    &&(
    0.42
     clotting
    0.42
    accumulation
    0.42
     satisfactory
    0.41
    খালী
    0.41
     hovering
    0.40
     smears
    0.39
    POSITIVE LOGITS
    კ
    0.46
     紅
    0.45
    ก
    0.45
     മാ
    0.44
     從
    0.44
    าร์
    0.44
     拉
    0.44
     همکاری
    0.43
     ఆర్
    0.43
    NOTA
    0.43
    Activations Density 0.000%

    No Known Activations