© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130082
    Prev
    Next
    INDEX
    Explanations

    code delimiters and keywords

    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_22/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
     школа
    -0.97
     菇
    -0.91
    ストール
    -0.90
    cadre
    -0.90
     acteur
    -0.89
     spektak
    -0.89
     enthou
    -0.89
     compagnon
    -0.88
     katastro
    -0.87
     Kräuter
    -0.86
    POSITIVE LOGITS
    𝚅
    0.86
    Of
    0.84
    öf
    0.83
     глу
    0.82
    IANE
    0.81
     điểm
    0.80
    To
    0.79
    éna
    0.78
     If
    0.77
    If
    0.75
    Activations Density 0.016%

    No Known Activations