© 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. 81744
    Prev
    Next
    INDEX
    Explanations

    about the

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

    architecture, database, specific examples

    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
     рациона
    0.47
     parfois
    0.46
    荭
    0.46
     hypothes
    0.46
    Según
    0.45
     mediums
    0.45
     ortodox
    0.44
     Эн
    0.44
     hence
    0.44
     recesses
    0.44
    POSITIVE LOGITS
    у
    0.49
    usz
    0.44
    \|^
    0.42
     VOICE
    0.42
    launcher
    0.41
    utama
    0.41
     Directory
    0.41
     SUBSCRIBE
    0.41
     Display
    0.40
     Launcher
    0.40
    Activations Density 0.004%

    No Known Activations