© 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. 94879
    Prev
    Next
    INDEX
    Explanations

    specific nouns and prepositions

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

    "First," followed by sentence

    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
    Мне
    0.54
    ಹಾ
    0.50
    ப்பட்டுள்ளது
    0.50
    गौरतलब
    0.48
    ರ್
    0.47
     aggrieved
    0.47
     publicized
    0.47
    ಫ
    0.46
    बता
    0.46
    給我
    0.46
    POSITIVE LOGITS
     전략
    0.66
     등에
    0.64
     것에
    0.63
     연구
    0.60
     등의
    0.60
     교육
    0.59
     다양한
    0.58
     위한
    0.57
     일부
    0.57
     전문
    0.56
    Activations Density 0.000%

    No Known Activations