© 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. 749
    Prev
    Next
    INDEX
    Explanations

    messages in multiple languages

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

    messages or communication

    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
     arginine
    0.47
    UTH
    0.42
    MEDICAL
    0.42
     proteine
    0.41
     acyl
    0.41
     artery
    0.40
    脓
    0.40
     細胞
    0.39
     oxidase
    0.39
     医学
    0.39
    POSITIVE LOGITS
     message
    0.72
     messages
    0.70
    メッセージ
    0.66
    message
    0.66
     mensaje
    0.63
     메시
    0.63
     mensajes
    0.61
     mesaj
    0.59
     warning
    0.59
     Message
    0.58
    Activations Density 0.019%

    No Known Activations