© 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. 64639
    Prev
    Next
    INDEX
    Explanations

    variety, different, comparative, novel

    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
     опять
    -0.85
     (\
    -0.84
     necessitated
    -0.77
     сказал
    -0.75
     exista
    -0.74
    íamos
    -0.73
     there
    -0.73
     again
    -0.73
    節約
    -0.71
     this
    -0.70
    POSITIVE LOGITS
     Descubre
    1.00
     Brits
    0.98
    eval
    0.91
    たしか
    0.91
    色んな
    0.89
    为啥
    0.87
     semej
    0.87
     Amérique
    0.87
     Estados
    0.86
    ereum
    0.86
    Activations Density 0.004%

    No Known Activations