© 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. 125101
    Prev
    Next
    INDEX
    Explanations

    specific institutions and professions

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

    request for threat

    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
    入院
    0.46
    ][[
    0.45
     বিজ্ঞান
    0.44
    )[[
    0.44
    PPtr
    0.43
    gano
    0.43
    bible
    0.43
    ጤ
    0.43
    뻤
    0.42
     یورو
    0.42
    POSITIVE LOGITS
     陳
    0.46
     magicians
    0.45
    ន៍
    0.45
    ерт
    0.44
     compone
    0.44
     colored
    0.44
    ьо
    0.43
     lessen
    0.43
     shrink
    0.42
     suffer
    0.42
    Activations Density 0.000%

    No Known Activations