© 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. 163841
    Prev
    Next
    INDEX
    Explanations

    your organization weddings

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

    already know

    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
    𓍊
    0.52
     同じ
    0.49
     Hoffmann
    0.47
     சுரே
    0.47
     Gerard
    0.46
    сибо
    0.46
     Andrés
    0.46
    êne
    0.46
     اسٹی
    0.45
     textes
    0.45
    POSITIVE LOGITS
    at
    0.48
     stocked
    0.46
     stoked
    0.45
     docket
    0.44
    begin
    0.42
    Ꭶ
    0.42
    const
    0.42
     lax
    0.42
     within
    0.41
    gly
    0.41
    Activations Density 0.000%

    No Known Activations