© 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. 34-GEMMASCOPE-RES-131K
    7. 58619
    Prev
    Next
    INDEX
    Explanations

    phrases starting with 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_34/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
    oudoune
    -0.91
     本店
    -0.85
     hır
    -0.84
    drawable
    -0.83
     curto
    -0.81
    燴
    -0.81
     mów
    -0.80
    rament
    -0.80
     responseData
    -0.80
    훅
    -0.79
    POSITIVE LOGITS
    ACIÓN
    0.83
     Kats
    0.80
     sleep
    0.79
     sobriety
    0.79
    ALLO
    0.78
    晶
    0.76
    ֳ
    0.76
    小学
    0.76
     الأطفال
    0.76
    묻
    0.74
    Activations Density 0.001%

    No Known Activations