© 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-3-270M-IT
    3. 12-GEMMASCOPE-2-RES-65K
    4. 1963
    Prev
    Next
    INDEX
    Explanations

    gender identity and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     diperlukan
    1.75
     dimaksud
    1.55
     据
    1.46
    indexPath
    1.45
     Evidence
    1.45
     verhindert
    1.43
     estoppel
    1.41
    verifier
    1.41
    że
    1.36
     速
    1.35
    POSITIVE LOGITS
     unisex
    1.65
     inhaling
    1.63
     solitude
    1.60
     brightly
    1.58
     jardin
    1.56
     trabajar
    1.53
     کھیلنا
    1.52
     listening
    1.50
     cuddling
    1.50
    oplus
    1.50
    Activations Density 0.362%

    No Known Activations