© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 109490
    Prev
    Next
    INDEX
    Explanations

    tech terms and companies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    했지만
    0.50
     있지만
    0.47
    不对
    0.44
     ज्यादातर
    0.44
     절
    0.43
     लेकिन
    0.42
    <unused1086>
    0.42
     advise
    0.42
    亚太
    0.42
    ारखंड
    0.42
    POSITIVE LOGITS
    Ἥ
    0.44
    每個
    0.41
    嘩
    0.40
    ייה
    0.40
     massac
    0.40
    たちが
    0.39
     vécu
    0.39
    感を
    0.39
    </u>
    0.38
     vivre
    0.38
    Activations Density 0.006%

    No Known Activations