© 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. 201287
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs followed by predicable words

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

    cost budget accommodation

    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
    umbrella
    0.45
    z
    0.44
    gallant
    0.43
    pumpkin
    0.43
     দার্শন
    0.43
    finger
    0.42
     WARREN
    0.42
    🤌
    0.42
    Soda
    0.41
     आगाज
    0.40
    POSITIVE LOGITS
     encour
    0.44
     zouden
    0.43
    하였
    0.43
    的消息
    0.43
     allein
    0.43
     シル
    0.43
     pály
    0.42
     colabor
    0.42
    ण्यात
    0.42
    ued
    0.41
    Activations Density 0.000%

    No Known Activations