© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 1517
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    她在
    2.64
     biographer
    2.60
    他在
    2.58
    佢
    2.56
     adjournment
    2.51
     Organisation
    2.42
    ouncement
    2.41
     organisation
    2.39
     favourites
    2.38
    Organisation
    2.36
    POSITIVE LOGITS
    rinsic
    2.74
     combust
    2.38
     emit
    2.37
    7
    2.32
    츠
    2.30
     constitut
    2.28
     respir
    2.27
     субъек
    2.27
     хоте
    2.24
     obey
    2.23
    Activations Density 0.647%

    No Known Activations