© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 7406
    Prev
    Next
    INDEX
    Explanations

    See the NOTICE file

    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
    ٦
    -1.88
     colocando
    -1.70
    MAXN
    -1.63
     Jego
    -1.60
     benutzt
    -1.54
    ٨
    -1.53
    ٤
    -1.52
     cuyos
    -1.48
     gdzie
    -1.45
     któ
    -1.43
    POSITIVE LOGITS
     if
    2.03
     the
    1.98
    引用元
    1.55
     konusu
    1.53
     inova
    1.45
    ****
    1.42
    のご紹介
    1.42
    引言
    1.38
     ayakkabı
    1.38
    冋
    1.38
    Activations Density 0.002%

    No Known Activations