© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 148311
    Prev
    Next
    INDEX
    Explanations

    image file extensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Allentown
    0.90
    ៤
    0.85
    lowest
    0.81
     localidad
    0.80
     descrizione
    0.79
    ოველ
    0.77
    %-
    0.76
    ೩
    0.76
    тивные
    0.75
     предназна
    0.75
    POSITIVE LOGITS
     so
    0.82
     imposes
    0.74
     impose
    0.69
     onto
    0.68
     removed
    0.67
    டா
    0.67
     Roxy
    0.64
     somehow
    0.64
     plucked
    0.64
     would
    0.63
    Activations Density 0.001%

    No Known Activations