© 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. 165098
    Prev
    Next
    INDEX
    Explanations

    special information

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

    economic interdependence

    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
    dod
    0.53
     It
    0.50
    gruppen
    0.50
    g
    0.50
     You
    0.49
    elling
    0.48
    c
    0.48
    ok
    0.48
    n
    0.46
     from
    0.46
    POSITIVE LOGITS
    უშა
    0.51
     permintaan
    0.50
    は
    0.49
     diminu
    0.49
    ثله
    0.49
    ント
    0.48
    늠
    0.48
    зировать
    0.48
    虜
    0.48
    вніш
    0.48
    Activations Density 0.000%

    No Known Activations