© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 66086
    Prev
    Next
    INDEX
    Explanations

    file paths and code

    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
    ściej
    -0.70
    usus
    -0.67
     herhangi
    -0.67
     comodidad
    -0.65
    loxy
    -0.64
    MHC
    -0.63
     producido
    -0.63
     swoją
    -0.62
    Twee
    -0.61
     proporcionar
    -0.61
    POSITIVE LOGITS
    wości
    0.69
     Italiano
    0.68
    страи
    0.68
    Adap
    0.67
     habilit
    0.66
     Instru
    0.66
     intr
    0.66
    controlling
    0.65
     Shore
    0.65
     flashback
    0.65
    Activations Density 0.064%

    No Known Activations