© 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. 195740
    Prev
    Next
    INDEX
    Explanations

    Polish American compiled

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

    government regulation and policy

    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
    مرار
    0.51
     obscur
    0.50
    داء
    0.46
    獄
    0.46
    هل
    0.46
    ቆ
    0.46
    晧
    0.45
    数は
    0.45
    failures
    0.45
    饒
    0.44
    POSITIVE LOGITS
    leti
    0.47
    ႃ
    0.47
    ząd
    0.46
    Ľ
    0.44
     зна
    0.44
     heartily
    0.43
    ăn
    0.42
     अभिगमन
    0.42
    你了
    0.42
    acja
    0.42
    Activations Density 0.000%

    No Known Activations