© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 176513
    Prev
    Next
    INDEX
    Explanations

    year projections, cat boxes, share our

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

    and battery

    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
    Negative Logits
    <start_of_turn>
    0.55
     छव
    0.53
     архив
    0.52
    ego
    0.51
    DrvGPIO
    0.51
    ógio
    0.51
     সুষ্ঠ
    0.50
    emin
    0.50
    chst
    0.49
    𝗵
    0.49
    POSITIVE LOGITS
     la
    0.55
     Coates
    0.50
     perquè
    0.48
     La
    0.47
     fag
    0.45
    ARG
    0.44
    脱
    0.43
    mtable
    0.43
    Co
    0.42
    定番
    0.42
    Activations Density 0.000%

    No Known Activations