© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71126
    Prev
    Next
    INDEX
    Explanations

    impressed by or with

    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
    N
    -3.09
     It
    -2.89
    ăzi
    -2.83
    迓
    -2.75
     revived
    -2.63
    同伴
    -2.59
     be
    -2.59
    舁
    -2.53
    enablog
    -2.50
    }$,
    -2.48
    POSITIVE LOGITS
    .
    3.11
    踅
    2.41
     leeftijd
    2.33
    
    2.22
     兩
    2.13
     綠
    2.13
    檍
    2.11
    讨厌
    2.09
    warnai
    2.08
     daer
    2.05
    Activations Density 0.002%

    No Known Activations