© 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-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-65K
    4. 5837
    Prev
    Next
    INDEX
    Explanations

    .org, .ie, .sh, .fabric

    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_65k_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
     tangential
    0.75
     hyperbol
    0.69
    pheus
    0.69
    ല
    0.65
     alkal
    0.63
    tox
    0.62
     Rama
    0.62
     fully
    0.61
    姆斯
    0.60
     cylinder
    0.60
    POSITIVE LOGITS
     FLA
    0.98
     FF
    0.91
     Fla
    0.90
     FS
    0.90
    FN
    0.89
     FTA
    0.88
    Ֆ
    0.88
     ஃ
    0.86
     FT
    0.86
     FGFR
    0.84
    Activations Density 0.391%

    No Known Activations