© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1899
    Prev
    Next
    INDEX
    Explanations

    questions about properties and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     envisaged
    1.15
     весьма
    1.02
     engender
    0.92
     idios
    0.89
     великолеп
    0.87
    頗
    0.87
     envisage
    0.86
    颇
    0.85
     requisite
    0.85
     envis
    0.85
    POSITIVE LOGITS
     objects
    0.99
     liquids
    0.96
     scientist
    0.95
     rocks
    0.93
     weathering
    0.92
     volcanoes
    0.91
     gases
    0.91
     plants
    0.91
     substances
    0.91
    ____________
    0.89
    Activations Density 0.140%

    No Known Activations