© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30636
    Prev
    Next
    INDEX
    Explanations

    names and syllables

    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
     ugy
    -0.85
    ZER
    -0.84
     pesados
    -0.83
     mik
    -0.82
    xtension
    -0.81
    ResourceBundle
    -0.81
    nen
    -0.79
     ս
    -0.78
     здания
    -0.77
    nek
    -0.77
    POSITIVE LOGITS
     případě
    0.81
     VIEWS
    0.79
     prefixed
    0.79
     Conj
    0.76
     sombrero
    0.76
     Chats
    0.75
    views
    0.75
     McF
    0.75
    .¹
    0.73
     occured
    0.73
    Activations Density 0.023%

    No Known Activations