© 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. 200074
    Prev
    Next
    INDEX
    Explanations

    citation (eds.)

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

    describing abstract concepts

    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
    ロン
    0.51
    Indicator
    0.47
    ")));
    0.45
    ↵
    0.45
    מים
    0.45
    Close
    0.43
    lara
    0.43
    lari
    0.42
    ]));
    0.42
    lardan
    0.42
    POSITIVE LOGITS
     Hasbro
    0.55
     Adder
    0.49
     Wohn
    0.49
     Citro
    0.49
     နှင့်
    0.48
     เวอร์
    0.48
     플레이
    0.47
     tampilan
    0.47
     الصفحة
    0.47
     Giz
    0.47
    Activations Density 0.000%

    No Known Activations