© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 1674
    Prev
    Next
    INDEX
    Explanations

    list any variety of

    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_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
     event
    0.79
     timescales
    0.77
     cohort
    0.75
    趟
    0.74
     breakdowns
    0.73
     clots
    0.70
     cohorts
    0.70
     caucus
    0.67
     structure
    0.65
     segment
    0.65
    POSITIVE LOGITS
    
    1.76
     qualsiasi
    1.73
     ойнотуу
    1.66
     различных
    1.64
    툐
    1.61
     различные
    1.56
     BSTC
    1.55
     любые
    1.54
     commercially
    1.54
     qualunque
    1.53
    Activations Density 2.113%

    No Known Activations