© 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. 434
    Prev
    Next
    INDEX
    Explanations

    when dealing

    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
     semoga
    1.91
    が進
    1.89
     calendário
    1.89
     Organisation
    1.88
     adjournment
    1.86
     organisers
    1.85
    囝
    1.85
     منصوبہ
    1.84
    inerary
    1.81
     biographer
    1.80
    POSITIVE LOGITS
    7
    2.41
     habitable
    2.27
     distinguishable
    2.17
    8
    2.16
    6
    2.12
    5
    2.09
     perceived
    1.97
     gray
    1.96
     meaningful
    1.95
     disconnected
    1.94
    Activations Density 0.597%

    No Known Activations