© 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. 69993
    Prev
    Next
    INDEX
    Explanations

    adverbs ending in -ly

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

    specific advice or instructions

    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
    პ
    0.47
    ਪ
    0.47
     เก
    0.47
    کل
    0.46
     ヨコハマ
    0.45
     resultar
    0.44
     città
    0.43
    پ
    0.43
    カ
    0.43
     unremarkable
    0.43
    POSITIVE LOGITS
     Motivational
    0.42
    干燥
    0.41
     निर्माण
    0.40
    ज्ञापन
    0.40
     EVO
    0.40
    饴
    0.40
    邑
    0.40
     Motiv
    0.40
    >$
    0.40
    ffekt
    0.40
    Activations Density 0.000%

    No Known Activations