© 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. 103572
    Prev
    Next
    INDEX
    Explanations

    personal and textual elements

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

    brother, talking, vibrate

    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
    Мы
    0.48
    astar
    0.47
    d
    0.46
    َل
    0.45
    ime
    0.44
     также
    0.44
    দ
    0.43
     expects
    0.43
     stockholders
    0.43
     motherhood
    0.42
    POSITIVE LOGITS
    esquerdo
    0.47
     Lí
    0.45
     flickering
    0.45
     textField
    0.44
    סטי
    0.43
    専
    0.43
    谚
    0.42
    ער
    0.41
     textura
    0.41
     selectInput
    0.41
    Activations Density 0.001%

    No Known Activations