© 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. 34-GEMMASCOPE-RES-131K
    7. 108689
    Prev
    Next
    INDEX
    Explanations

    Reviews, hours, returns

    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
     /\.(
    -0.91
    وفة
    -0.91
     sapi
    -0.87
     sinistra
    -0.86
     raad
    -0.85
     rappeler
    -0.84
     rapido
    -0.84
     tehn
    -0.82
     kambing
    -0.81
    éens
    -0.80
    POSITIVE LOGITS
     COVID
    0.87
     speak
    0.84
     closest
    0.82
     covid
    0.82
     pc
    0.81
    <0xF3>
    0.80
    デオ
    0.78
     CTV
    0.75
    úsica
    0.73
     ...
    0.73
    Activations Density 0.002%

    No Known Activations