© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 53013
    Prev
    Next
    INDEX
    Explanations

    countries and specific names

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

    describing condition or degree

    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
    Not in Any Lists

    No Comments

    Negative Logits
    0.51
    𝟐
    0.45
     comorbid
    0.43
    体制
    0.42
    testimon
    0.41
    新型
    0.41
    有了
    0.41
    ண்ண
    0.40
    拟
    0.40
    报考
    0.40
    POSITIVE LOGITS
     Barcelona
    0.45
     Algeria
    0.44
     ډاونلوډ
    0.42
     غ
    0.41
    嶆
    0.40
     Qatar
    0.40
     Wales
    0.39
     smugg
    0.39
     Ireland
    0.39
     Shane
    0.39
    Activations Density 0.000%

    No Known Activations