© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 2015
    Prev
    Next
    INDEX
    Explanations

    the [concept/entity]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_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
    .
    1.77
    The
    1.77
    1
    1.76
    2
    1.73
     to
    1.72
     a
    1.66
    <0xF3>
    1.66
    ,
    1.63
     The
    1.62
     and
    1.61
    POSITIVE LOGITS
    𒀕
    1.67
     मानबी
    1.65
    퍁
    1.64
     व्यपहरण
    1.64
     givenChar
    1.64
    <unused1182>
    1.61
     nCharString
    1.61
     क़ुर्आन
    1.61
    𒌇
    1.60
     vattum
    1.60
    Activations Density 1.146%

    No Known Activations