© 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. 75436
    Prev
    Next
    INDEX
    Explanations

    "kind of" followed by description

    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
    ↵
    -0.88
    چ
    -0.79
    roč
    -0.77
     infinites
    -0.75
     unconventional
    -0.75
    Grupos
    -0.73
    similiano
    -0.73
     diligent
    -0.73
    怎么了
    -0.72
    andidat
    -0.72
    POSITIVE LOGITS
    hearted
    1.29
     of
    1.16
     hearted
    1.15
    辞典
    1.04
    “”
    1.03
    gom
    0.99
     Gesù
    0.95
     DbType
    0.94
    fikasi
    0.91
    hev
    0.90
    Activations Density 0.016%

    No Known Activations