© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 29074
    Prev
    Next
    INDEX
    Explanations

    announcements, notices, or beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     terapeut
    0.35
    سكري
    0.35
    compos
    0.34
    üedad
    0.34
    🔅
    0.32
    ʤ
    0.32
    ㊙
    0.32
    🐠
    0.32
     antitumor
    0.32
    ంచరీలు
    0.32
    POSITIVE LOGITS
     announcements
    0.39
     Announcements
    0.38
     הס
    0.38
     commencer
    0.37
                                   
    0.37
     Hopefully
    0.37
     beginnen
    0.36
     Notices
    0.36
     Revelation
    0.35
    )"
    0.34
    Activations Density 0.000%

    No Known Activations