© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 1063
    Prev
    Next
    INDEX
    Explanations

    politeness and requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_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
    tions
    0.95
     Reason
    0.89
     Material
    0.88
     Route
    0.88
     Measure
    0.88
    ,
    0.88
    R
    0.86
     Market
    0.85
    čení
    0.85
     Museum
    0.84
    POSITIVE LOGITS
    𝒎
    1.07
    स
    1.05
    Saludos
    1.03
    vollen
    1.00
    incere
    0.99
    ляю
    0.98
    كم
    0.96
     😊
    0.96
    1
    0.96
    2
    0.96
    Activations Density 2.095%

    No Known Activations