© 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. 66200
    Prev
    Next
    INDEX
    Explanations

    what do you

    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
     alkoholu
    -1.09
     innych
    -1.02
     patrie
    -0.97
    НОЕ
    -0.96
     baterie
    -0.94
     haine
    -0.93
    bezpiecz
    -0.93
     psicológico
    -0.92
    ˥
    -0.91
     SOUTH
    -0.91
    POSITIVE LOGITS
    owieck
    1.09
    制
    0.96
     качестве
    0.96
    作为
    0.93
     affording
    0.88
    了解
    0.87
    iseerd
    0.87
     вместо
    0.86
     keluarganya
    0.85
    !);
    0.85
    Activations Density 0.003%

    No Known Activations