© 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. 42345
    Prev
    Next
    INDEX
    Explanations

    Reed names and reeds

    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
    翃
    -2.84
     neuen
    -2.81
    しないと
    -2.67
    軚
    -2.56
    ㇼ
    -2.52
    ⸂
    -2.48
     Hinblick
    -2.48
    
    -2.44
    峮
    -2.42
     positiven
    -2.38
    POSITIVE LOGITS
     It
    3.00
    ÇÕES
    3.00
    沺
    2.61
    勦
    2.47
    衎
    2.47
     pernikahan
    2.41
     modalités
    2.33
    ")]
    2.33
    ႐
    2.33
    勍
    2.31
    Activations Density 0.003%

    No Known Activations