© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 12503
    Prev
    Next
    INDEX
    Explanations

    drum beat or drumming

    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
    Negative Logits
    ت
    4.40
    𝘨
    4.04
    ট
    4.02
    𝘵
    3.97
    𝘩
    3.62
    р
    3.55
    تام
    3.53
    𝘴
    3.53
    𝘦
    3.43
    𝘬
    3.32
    POSITIVE LOGITS
     houdt
    3.45
    те
    3.15
    وت
    3.12
    न
    3.00
    retval
    2.95
     millones
    2.94
    ू
    2.92
    к
    2.88
    𝗥
    2.87
    ण
    2.85
    Activations Density 0.089%

    No Known Activations