© 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. 1032
    Prev
    Next
    INDEX
    Explanations

    tax

    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
    Designs
    0.72
     meninos
    0.70
     nitro
    0.68
     chicks
    0.67
     vody
    0.66
     puppies
    0.64
    雏
    0.64
     labios
    0.63
    Meer
    0.62
     ales
    0.62
    POSITIVE LOGITS
     tax
    2.56
     Tax
    2.52
     Taxes
    2.40
     taxes
    2.39
    Tax
    2.34
    tax
    2.28
     Taxation
    2.25
     taxation
    2.19
     TAX
    2.08
    税
    2.06
    Activations Density 3.649%

    No Known Activations