© 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
    2. Gemma-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-16K
    4. 12299
    Prev
    Next
    INDEX
    Explanations

    state or action method

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
     маркетин
    1.13
     คณิต
    1.13
     transitioning
    1.13
     unlocking
    1.12
    ඵ
    1.11
     opportune
    1.10
     fracking
    1.07
     integrating
    1.06
     sát
    1.05
     ♡
    1.04
    POSITIVE LOGITS
    或
    0.80
    ou
    0.75
     і
    0.75
     And
    0.70
     It
    0.70
     یا
    0.69
    it
    0.68
     You
    0.67
    ாவது
    0.66
     বলুন
    0.66
    Activations Density 0.002%

    No Known Activations