© 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. 14154
    Prev
    Next
    INDEX
    Explanations

    technical terms and categories

    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
     থাকতেন
    0.43
    Прави
    0.41
     সম
    0.41
     posuere
    0.40
    ᕝ
    0.40
     aDAO
    0.38
    Voilà
    0.38
     pseudos
    0.38
     वनस्पती
    0.38
    饮食
    0.38
    POSITIVE LOGITS
    ↵
    0.48
    ين
    0.43
    ボリー
    0.42
    uin
    0.41
     utilizzando
    0.39
    ASH
    0.38
    lic
    0.38
    ap
    0.38
    received
    0.37
     ||
    0.37
    Activations Density 0.028%

    No Known Activations