© 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. 22-GEMMASCOPE-2-RES-262K
    7. 14993
    Prev
    Next
    INDEX
    Explanations

    you might also like

    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_22_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
     charitable
    0.63
     assistance
    0.63
    Cory
    0.62
     thoughtful
    0.61
    '.$
    0.59
     philanthropy
    0.59
     మాట
    0.58
     adv
    0.58
     cip
    0.58
     ridd
    0.57
    POSITIVE LOGITS
     Collectively
    0.84
     gostar
    0.84
     লিখ
    0.80
     coronae
    0.80
     Interest
    0.79
     tijdens
    0.78
     insuffis
    0.78
    uxi
    0.78
    ੲ
    0.77
    เข้า
    0.77
    Activations Density 0.004%

    No Known Activations