© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 66130
    Prev
    Next
    INDEX
    Explanations

    post

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

    MongoDB documents

    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
    nl
    0.46
    CH
    0.42
    GB
    0.41
    宁
    0.41
    inot
    0.41
    GF
    0.41
    uft
    0.41
    ງ
    0.40
    EST
    0.40
    ναν
    0.40
    POSITIVE LOGITS
    бенок
    0.47
     şirket
    0.47
     സത്യ
    0.46
     transactions
    0.46
     şirk
    0.46
     işlem
    0.46
    با
    0.45
     edildi
    0.45
     شرکت
    0.45
     entreprises
    0.45
    Activations Density 0.002%

    No Known Activations