© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2342
    Prev
    Next
    INDEX
    Explanations

    preparing or making something

    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
    rinsic
    0.90
    6
    0.83
    own
    0.78
    跖
    0.73
     بخشی
    0.71
    ６
    0.70
    охра
    0.70
     fermionic
    0.70
    科学院
    0.70
    utis
    0.69
    POSITIVE LOGITS
     =>
    2.20
    =>
    1.65
     =>{
    1.45
    =>$
    1.36
    =>{
    1.35
     Kah
    1.22
     lever
    1.21
     Strategy
    1.20
     Alk
    1.17
     Reh
    1.16
    Activations Density 0.023%

    No Known Activations