© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 90334
    Prev
    Next
    INDEX
    Explanations

    Basque heritage and place names

    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
    Not in Any Lists

    No Comments

    Negative Logits
     países
    0.42
    馇
    0.41
     Mujeres
    0.40
     dünyanın
    0.39
    澳大利亚
    0.39
     쭉
    0.38
    माष्टमी
    0.38
    捭
    0.37
    ര്യ
    0.37
     बेटर
    0.37
    POSITIVE LOGITS
     (
    0.38
     overridden
    0.38
     correctness
    0.37
     fname
    0.37
     interpolated
    0.36
     $($
    0.36
     proti
    0.35
     সংবাদ
    0.35
    $('#
    0.35
     vd
    0.35
    Activations Density 0.003%

    No Known Activations