© 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. 11394
    Prev
    Next
    INDEX
    Explanations

    Ginger, reflect, accused

    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
     അവസ്ഥ
    0.55
     چاہے
    0.51
    㫧
    0.47
    لیل
    0.47
     দর্শক
    0.46
    tség
    0.46
     ಆದ
    0.46
    洏
    0.46
     நேரம்
    0.46
     nécess
    0.45
    POSITIVE LOGITS
    it
    0.55
     other
    0.53
     more
    0.46
     has
    0.46
     coupon
    0.45
    IT
    0.44
     can
    0.44
     winter
    0.44
     produce
    0.44
     BTU
    0.43
    Activations Density 0.013%

    No Known Activations