© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 192613
    Prev
    Next
    INDEX
    Explanations

    writing professional fields

    np_acts-logits-general · gemini-2.5-flash-lite

    characters and contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     উপন
    0.51
     venne
    0.45
     Spell
    0.44
     Simpl
    0.44
     POSSIBILITY
    0.44
     ATH
    0.44
    ्रिक
    0.43
    )],
    0.43
     PUP
    0.43
     odstr
    0.43
    POSITIVE LOGITS
     during
    0.46
     habituellement
    0.46
    ic
    0.46
    ใจ
    0.45
    心
    0.44
    water
    0.44
    in
    0.43
    在新
    0.43
    abag
    0.43
    during
    0.43
    Activations Density 0.001%

    No Known Activations