© 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-65K
    7. 11904
    Prev
    Next
    INDEX
    Explanations

    matches any character

    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_65k_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
     a
    0.49
    Tomorrow
    0.47
     etapas
    0.47
    CIP
    0.46
     massima
    0.45
    抗
    0.45
     futura
    0.45
    tomorrow
    0.45
    NERS
    0.45
    進
    0.45
    POSITIVE LOGITS
    的机会
    0.52
    ofen
    0.52
    的游戏
    0.49
    ulsion
    0.47
    ürz
    0.46
    urance
    0.46
    逐漸
    0.45
    urs
    0.45
    nal
    0.45
     ریک
    0.45
    Activations Density 0.009%

    No Known Activations