© 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. 16704
    Prev
    Next
    INDEX
    Explanations

    measurement units and actions

    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
    0
    0.68
     incluyendo
    0.48
     orchestrated
    0.48
    9
    0.48
    4
    0.47
    5
    0.46
    አ
    0.46
    {
    0.45
    ዐ
    0.45
     gobierno
    0.44
    POSITIVE LOGITS
     vaikka
    0.49
    鏟
    0.49
     putt
    0.46
    ocortic
    0.44
    क्राइब
    0.43
    ្នក
    0.43
    metter
    0.42
    farbe
    0.42
    莒
    0.42
    䣨
    0.42
    Activations Density 0.008%

    No Known Activations