© 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. 18965
    Prev
    Next
    INDEX
    Explanations

    months May through August

    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
     límite
    0.75
    ón
    0.69
    ]*
    0.69
    xlsx
    0.68
    return
    0.66
    极限
    0.66
    यदि
    0.66
    Qui
    0.66
     qui
    0.65
     واحد
    0.65
    POSITIVE LOGITS
    忪
    0.64
    LowerCase
    0.64
     obligé
    0.62
     imperatives
    0.62
    เบ
    0.60
     preamble
    0.60
     microcosm
    0.59
     вспом
    0.59
    Provenance
    0.59
     వి
    0.59
    Activations Density 0.052%

    No Known Activations