© 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. 36076
    Prev
    Next
    INDEX
    Explanations

    Cost, restructuring, things

    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
     南
    0.48
    ボディ
    0.46
     さらに
    0.45
     드러
    0.45
     propelled
    0.45
     intérêt
    0.44
     チ
    0.44
     chimique
    0.44
     機能
    0.44
     देऊन
    0.43
    POSITIVE LOGITS
    verters
    0.49
    ল
    0.46
    Pixel
    0.46
    Z
    0.44
    Cow
    0.44
    Metal
    0.44
    Parameter
    0.44
    Random
    0.44
    Tính
    0.44
    DataFrame
    0.44
    Activations Density 0.022%

    No Known Activations