© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 34596
    Prev
    Next
    INDEX
    Explanations

    item descriptions and specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mantra
    -0.82
    <0x80>
    -0.82
     ligue
    -0.82
     arroyo
    -0.81
     shippuden
    -0.80
    ásban
    -0.78
     nasel
    -0.77
    登陆
    -0.77
     рестайлинг
    -0.76
    Sklici
    -0.76
    POSITIVE LOGITS
     zwölf
    0.81
    definecolor
    0.79
     باشند
    0.76
    ūras
    0.73
     caminha
    0.72
    AMO
    0.72
     pompous
    0.72
     Vorles
    0.72
     cascades
    0.71
     acredita
    0.71
    Activations Density 0.001%

    No Known Activations