© 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. 195526
    Prev
    Next
    INDEX
    Explanations

    words after punctuation or conjunctions

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

    understanding the

    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
    もしくは
    0.47
    wing
    0.45
    <0x80>
    0.43
    ilium
    0.43
    あるいは
    0.42
    願い
    0.41
    Profit
    0.41
    ways
    0.41
     weight
    0.41
    books
    0.41
    POSITIVE LOGITS
    attup
    0.47
     圆
    0.45
    楎
    0.44
    喷
    0.43
    సుకొ
    0.43
    }`);
    0.43
     укреп
    0.43
     недвижимости
    0.43
    ্ল্ড
    0.43
    粑
    0.43
    Activations Density 0.001%

    No Known Activations