© 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. 51710
    Prev
    Next
    INDEX
    Explanations

    numbers or technical terms followed by specific words

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

    tokens after "False."

    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
    ◇
    0.57
     آینده
    0.54
    今後
    0.53
    未来的
    0.50
    厚
    0.49
    将来
    0.48
    向
    0.46
    未来
    0.46
     toekomst
    0.46
     फ्यूचर
    0.45
    POSITIVE LOGITS
     reversed
    0.49
     factories
    0.47
     confl
    0.46
     shit
    0.46
     bonded
    0.45
     palabra
    0.44
     fermented
    0.44
     ejected
    0.44
     cramped
    0.44
     camel
    0.44
    Activations Density 0.000%

    No Known Activations