© 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. 1604
    Prev
    Next
    INDEX
    Explanations

    contextual equations

    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
    佢
    2.91
     nombreux
    2.81
     adjournment
    2.78
    Organisation
    2.76
     Organisation
    2.72
     diarrhoea
    2.69
     aandacht
    2.69
    她在
    2.69
     organisation
    2.68
     Brides
    2.64
    POSITIVE LOGITS
    rinsic
    3.49
     emits
    3.35
     obey
    3.26
    7
    3.24
     belongs
    3.16
     belong
    3.12
    Diffuse
    3.09
     emit
    3.09
     combust
    3.09
     possesses
    3.08
    Activations Density 2.108%

    No Known Activations