© 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. 210567
    Prev
    Next
    INDEX
    Explanations

    family, react, walls, medieval

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

    heavy wooden door

    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
    م
    0.51
    بق
    0.50
    لق
    0.46
    м
    0.45
     аспек
    0.44
    псо
    0.44
    Purg
    0.43
    met
    0.43
    Publication
    0.43
    ম
    0.43
    POSITIVE LOGITS
     supernatants
    0.51
    ulfate
    0.50
     niobium
    0.50
     NDP
    0.49
     bitmaps
    0.47
     మహా
    0.47
     koi
    0.46
     কম্পিউ
    0.45
     serums
    0.44
     ఎమ్మె
    0.43
    Activations Density 0.000%

    No Known Activations