© 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. 193538
    Prev
    Next
    INDEX
    Explanations

    following specific sequences

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

    assessment, away, dignity, safe, crisis

    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
    malign
    0.57
     الأمريكي
    0.52
     malignant
    0.48
    dh
    0.48
    KES
    0.47
    ඪ
    0.47
     hydrochloric
    0.47
    mcs
    0.47
    mersive
    0.46
    chemicals
    0.46
    POSITIVE LOGITS
     naby
    0.47
     vær
    0.46
    ู้
    0.45
     स्टेट
    0.45
    ोरा
    0.43
     bruger
    0.43
     vär
    0.43
    増
    0.43
     rohkem
    0.43
     capitol
    0.42
    Activations Density 0.000%

    No Known Activations