© 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. 205675
    Prev
    Next
    INDEX
    Explanations

    check for bones

    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
     विदेशों
    0.45
    떄
    0.44
     طریق
    0.44
    ভিন
    0.44
     ਜ਼
    0.43
    TextView
    0.42
     Verarbeitung
    0.42
     सुपरहिट
    0.42
    टेगरी
    0.42
    HashMap
    0.41
    POSITIVE LOGITS
     a
    0.51
     at
    0.48
     talent
    0.48
    ?).
    0.46
    ”).
    0.43
     cosmic
    0.42
    ）.
    0.42
    ).
    0.42
     accomplish
    0.42
     YEAR
    0.41
    Activations Density 0.004%

    No Known Activations