© 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. 55662
    Prev
    Next
    INDEX
    Explanations

    installable, покуп, пользова

    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
    นั้น
    -0.88
     dizaine
    -0.82
    خرى
    -0.81
     Geräten
    -0.81
    siswa
    -0.78
    lical
    -0.77
    notas
    -0.77
     Rückseite
    -0.76
     partly
    -0.76
     courseId
    -0.76
    POSITIVE LOGITS
    aaa
    1.34
    aaaa
    1.28
    aa
    1.18
    aaaaaaaa
    1.06
    aaaaa
    1.01
    ぁ
    0.99
    en
    0.97
    ed
    0.93
    𝔪
    0.93
    ace
    0.91
    Activations Density 0.077%

    No Known Activations