© 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-262K
    4. 1005
    Prev
    Next
    INDEX
    Explanations

    years and months

    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
     musí
    0.84
     dowol
    0.69
    அல்ல
    0.68
     পারছি
    0.68
    anesulfonyl
    0.68
    ewords
    0.68
     ViewGroup
    0.67
    暂
    0.66
    rxjs
    0.66
    epochs
    0.66
    POSITIVE LOGITS
     בשנת
    3.19
     vuonna
    2.88
    ในปี
    2.82
     tahun
    2.19
     December
    2.13
     năm
    2.11
     July
    2.06
     January
    2.05
     mwaka
    2.04
     September
    2.01
    Activations Density 0.219%

    No Known Activations