© 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. 163144
    Prev
    Next
    INDEX
    Explanations

    Dominican Republic, Achilles held

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

    finding information related to finding things

    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
    lič
    0.47
    >∈</
    0.46
    上海
    0.43
    ankt
    0.43
    aille
    0.42
    誌
    0.41
    ",(
    0.41
     入
    0.41
    інки
    0.40
    AccessException
    0.40
    POSITIVE LOGITS
     corte
    0.54
     Geet
    0.51
     rhyth
    0.50
     donner
    0.48
     manly
    0.48
     dwellers
    0.46
     sottoline
    0.46
    водитель
    0.46
     colo
    0.45
     lengthened
    0.45
    Activations Density 0.000%

    No Known Activations