© 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. 9251
    Prev
    Next
    INDEX
    Explanations

    keywords followed by descriptions

    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
    y
    0.40
    ➛
    0.38
    gning
    0.38
    𠃍
    0.38
    nungen
    0.38
     to
    0.37
    ش
    0.36
     digraph
    0.36
    \
    0.35
    nings
    0.34
    POSITIVE LOGITS
    до
    0.38
    <unused1888>
    0.38
    <unused499>
    0.38
    <unused411>
    0.37
     Comité
    0.37
    <unused399>
    0.37
    ↵
    0.36
    <unused402>
    0.36
    <unused311>
    0.35
    <unused300>
    0.35
    Activations Density 0.383%

    No Known Activations