© 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. 496
    Prev
    Next
    INDEX
    Explanations

    order status

    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
     slides
    1.39
     method
    1.38
     strategy
    1.36
     is
    1.34
     v
    1.30
     methods
    1.29
     one
    1.24
     arrows
    1.22
     was
    1.21
     graphs
    1.21
    POSITIVE LOGITS
    7
    1.95
     lucht
    1.94
     dormitorio
    1.92
     departamentos
    1.84
    tres
    1.80
     identifik
    1.79
    rinsic
    1.79
     capitalismo
    1.79
     deportes
    1.76
    
    1.76
    Activations Density 0.258%

    No Known Activations