© 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. 48821
    Prev
    Next
    INDEX
    Explanations

    . property access

    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
    nový
    -0.96
    Pourquoi
    -0.92
    tinya
    -0.91
    就行
    -0.90
     ję
    -0.89
    ざま
    -0.89
     nehme
    -0.85
    ignty
    -0.85
    orElse
    -0.84
     شوید
    -0.84
    POSITIVE LOGITS
     tersebut
    1.07
     bahkan
    0.94
     it
    0.92
    lography
    0.89
     them
    0.88
    嘹
    0.88
     Although
    0.88
    Unisex
    0.86
    льники
    0.85
     koning
    0.85
    Activations Density 0.027%

    No Known Activations