© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 98543
    Prev
    Next
    INDEX
    Explanations

    javascript function($) pattern

    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
    Dazu
    -0.90
     navigateur
    -0.90
     bénéficiaire
    -0.88
     músicas
    -0.88
    ційний
    -0.87
     piatta
    -0.86
    igten
    -0.85
    довал
    -0.84
    Jetzt
    -0.84
     données
    -0.83
    POSITIVE LOGITS
     ($)
    1.20
     with
    0.97
     e
    0.97
     from
    0.94
     ($
    0.92
     at
    0.89
    자인
    0.89
    ()
    0.89
     ()
    0.87
    ($)
    0.87
    Activations Density 0.020%

    No Known Activations