© 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. 1888
    Prev
    Next
    INDEX
    Explanations

    material forms

    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
    Arqu
    -0.77
    janja
    -0.70
    
    -0.68
    dry
    -0.66
    enfants
    -0.66
    图案
    -0.65
     enviar
    -0.65
    ارج
    -0.64
    プター
    -0.64
     dry
    -0.63
    POSITIVE LOGITS
     bars
    2.27
     rods
    1.74
    bars
    1.70
     ing
    1.65
     Bars
    1.61
     bar
    1.57
    Bars
    1.52
     blocks
    1.51
     slabs
    1.50
     rod
    1.43
    Activations Density 0.093%

    No Known Activations