© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 7191
    Prev
    Next
    INDEX
    Explanations

    github, title, slug

    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
    teng
    -0.84
     Hundred
    -0.75
     découvrir
    -0.75
    风雨
    -0.68
     BOTTOM
    -0.68
    ุ่น
    -0.68
    cci
    -0.67
    Factory
    -0.66
     responsible
    -0.66
     gó
    -0.65
    POSITIVE LOGITS
     proprement
    0.68
     Хо
    0.66
    знание
    0.66
    Prezzo
    0.64
     verschill
    0.63
    umper
    0.63
    atleta
    0.63
     sûrement
    0.63
    шением
    0.63
     gasp
    0.63
    Activations Density 0.083%

    No Known Activations