© 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. 96780
    Prev
    Next
    INDEX
    Explanations

    followed by 'of' or 'and'

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

    trends and states

    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
    浲
    0.52
     แรก
    0.48
     चुने
    0.47
     BLUENRG
    0.47
    แรก
    0.46
    完毕
    0.46
    ledge
    0.46
    wl
    0.46
    aculate
    0.46
    лада
    0.46
    POSITIVE LOGITS
    FS
    0.52
    Monitor
    0.52
     subcontract
    0.51
    मॉ
    0.48
    Z
    0.48
     squire
    0.47
     Sains
    0.46
     chaper
    0.46
    List
    0.45
    PS
    0.45
    Activations Density 0.000%

    No Known Activations