© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12983
    Prev
    Next
    INDEX
    Explanations

    end of quoted speech

    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
    lík
    -0.88
    \#
    -0.85
    ++)
    
    -0.80
     MwSt
    -0.80
     カメラ
    -0.79
    gendes
    -0.78
     Lieferung
    -0.76
     treball
    -0.76
    NOT
    -0.75
    íp
    -0.75
    POSITIVE LOGITS
     minggu
    0.96
     those
    0.96
    refer
    0.94
     tersebut
    0.92
    tersebut
    0.89
     referring
    0.87
    larında
    0.85
    Edd
    0.85
     diketahui
    0.84
     indeed
    0.84
    Activations Density 0.006%

    No Known Activations