© 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. 148533
    Prev
    Next
    INDEX
    Explanations

    closed captions

    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
     Informed
    0.65
     жо
    0.64
     ox
    0.64
    atifs
    0.63
    หว
    0.63
    ueva
    0.62
    霖
    0.61
    既存
    0.61
     ऑक्स
    0.61
     Ärz
    0.61
    POSITIVE LOGITS
     crested
    0.69
     Fibonacci
    0.68
     REIT
    0.66
    idur
    0.66
     treści
    0.66
     Men
    0.66
    caption
    0.64
    protocol
    0.64
    ieras
    0.63
     laughing
    0.63
    Activations Density 0.002%

    No Known Activations