© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1265
    Prev
    Next
    INDEX
    Explanations

    list items or bullet points

    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_31_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
    0.87
        
    0.78
       
    0.75
    <0xE3>
    0.71
         
    0.65
      
    0.60
    \
    0.57
    <0xE2>
    0.54
     blocks
    0.54
    <0xC2>
    0.52
    POSITIVE LOGITS
     minimizar
    0.61
     ゴルフ
    0.60
     немає
    0.60
    ॕ
    0.60
     ذلك
    0.59
     evitar
    0.59
     innych
    0.59
    ങ
    0.58
    𝙄
    0.58
    Ⲉ
    0.58
    Activations Density 0.098%

    No Known Activations