© 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. 86800
    Prev
    Next
    INDEX
    Explanations

    festivals

    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
    迓
    -3.55
    媗
    -3.47
    ሷ
    -3.34
    
    -3.33
    牐
    -3.28
    鸲
    -3.20
    辚
    -3.14
    婠
    -3.09
    蟥
    -3.08
    珰
    -3.08
    POSITIVE LOGITS
     If
    4.06
    We
    2.86
    It
    2.83
    已经
    2.81
     The
    2.63
    用
    2.53
    If
    2.48
    When
    2.47
    可以
    2.39
    Perhaps
    2.39
    Activations Density 0.002%

    No Known Activations