© 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. 12480
    Prev
    Next
    INDEX
    Explanations

    arrival at a point

    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
    𝐭
    3.04
    𝐬
    2.87
    ことが
    2.83
    စိတ်အပိုင်း
    2.82
    েল
    2.78
    𝐝
    2.73
    নি
    2.63
    습니다
    2.63
    ীয়
    2.61
    ない
    2.59
    POSITIVE LOGITS
    ০
    4.67
    u
    4.07
    त
    3.59
    ia
    3.49
    a
    3.47
    و
    3.09
    e
    3.08
    ни
    3.07
    i
    3.02
    ie
    2.99
    Activations Density 0.068%

    No Known Activations