© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 47945
    Prev
    Next
    INDEX
    Explanations

    at followed by circumstances, time, or conditions

    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
     نیا
    0.41
     BASF
    0.40
    บริ
    0.39
     inherently
    0.39
    霓
    0.39
     botan
    0.39
    ン
    0.38
    沃尔
    0.38
    gies
    0.38
     performer
    0.37
    POSITIVE LOGITS
    οδο
    0.48
     ಚುನಾವಣ
    0.43
     election
    0.42
    election
    0.42
    ravés
    0.41
     pubb
    0.41
     رات
    0.40
     ఎన్నిక
    0.40
    二百
    0.39
     двадцать
    0.39
    Activations Density 0.018%

    No Known Activations