© 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. 131954
    Prev
    Next
    INDEX
    Explanations

    if followed by personal pronouns or only

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

    examples or lists

    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
     ช่อง
    0.51
     роках
    0.49
     నాలుగు
    0.46
     вересня
    0.45
    )
    0.45
    шт
    0.44
     сайті
    0.44
    개월
    0.44
    ા
    0.43
     Това
    0.43
    POSITIVE LOGITS
     ấy
    0.46
     reunião
    0.46
     reinado
    0.45
    传
    0.45
     eventos
    0.44
     hòa
    0.44
     periodistas
    0.44
     sinc
    0.43
     atmósfera
    0.43
     degener
    0.42
    Activations Density 0.000%

    No Known Activations