© 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. 40-GEMMASCOPE-2-RES-262K
    7. 11565
    Prev
    Next
    INDEX
    Explanations

    Cre variations and mentions

    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_40_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
     নবী
    0.40
    ヨー
    0.40
     வரு
    0.39
     BOY
    0.39
     kolejne
    0.38
     déprimées
    0.38
    ifik
    0.36
    փ
    0.36
     интегри
    0.36
    沍
    0.36
    POSITIVE LOGITS
    Cre
    0.68
     cre
    0.67
     кре
    0.63
    кре
    0.62
     Cre
    0.60
    cre
    0.56
    CRE
    0.54
     kre
    0.54
    Kre
    0.54
     Кре
    0.52
    Activations Density 0.006%

    No Known Activations