© 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. 111251
    Prev
    Next
    INDEX
    Explanations

    Aussie Icon PsExec Globals nagging

    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
    谖
    -3.34
    焄
    -2.91
    
    -2.80
    􀂃
    -2.70
    ſelves
    -2.70
    ו
    -2.55
    蕻
    -2.52
    
    -2.52
    ⤥
    -2.45
    ?
    -2.38
    POSITIVE LOGITS
    éphane
    2.61
    拶
    2.59
    杁
    2.52
    榇
    2.50
     видит
    2.50
    蠖
    2.45
    埽
    2.38
    تیجه
    2.38
    에도
    2.36
     kterou
    2.30
    Activations Density 0.002%

    No Known Activations