© 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. 9-GEMMASCOPE-2-RES-262K
    7. 8838
    Prev
    Next
    INDEX
    Explanations

    scriptural enumeration and clauses

    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_9_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
    ی
    1.07
    ्स
    1.04
    ে
    1.02
    ូន
    1.00
    ⬮
    0.98
    ا
    0.97
    ວດ
    0.96
    ことが
    0.94
    ्ट
    0.93
    。</
    0.93
    POSITIVE LOGITS
    о
    1.32
    j
    0.99
    acuse
    0.98
    а
    0.94
    inicio
    0.93
    ᧐
    0.92
    av
    0.91
    খানে
    0.90
    ())
    0.89
     revolved
    0.88
    Activations Density 0.006%

    No Known Activations