© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70478
    Prev
    Next
    INDEX
    Explanations

    names beginning with hark

    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_10/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
    حيان
    -2.27
    引用元
    -2.22
    Наталья
    -2.13
    ハロウィン
    -2.11
    说说
    -2.08
    ユニクロ
    -2.06
    鱚
    -2.02
    ဴ
    -2.02
    s
    -2.00
     inspiradoras
    -1.99
    POSITIVE LOGITS
    '
    2.98
    an
    2.69
     Then
    2.27
    就算
    1.96
     they
    1.95
     are
    1.95
     establece
    1.91
    那是
    1.91
    рее
    1.91
     hará
    1.90
    Activations Density 0.004%

    No Known Activations