© 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. 78680
    Prev
    Next
    INDEX
    Explanations

    separators and code comments

    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
           
    -0.90
     because
    -0.88
             
    -0.87
    立てる
    -0.85
    랜드
    -0.83
               
    -0.81
     тамо
    -0.81
     dealer
    -0.80
     never
    -0.80
    -0.80
    POSITIVE LOGITS
     チラ
    0.91
    LNG
    0.90
    தல்
    0.89
     bemerk
    0.89
    believe
    0.88
    batterie
    0.87
    bege
    0.85
     गर्
    0.84
    excellent
    0.84
    leyin
    0.84
    Activations Density 0.010%

    No Known Activations