© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 16011
    Prev
    Next
    INDEX
    Explanations

    numbers and commas

    np_acts-logits-general · gemini-2.5-flash-lite

    notes from context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bm
    0.50
     جذاب
    0.49
    &\
    0.49
    UM
    0.48
    DM
    0.48
    σουν
    0.46
    herme
    0.46
    <0x0B>
    0.46
    uan
    0.46
    Я
    0.45
    POSITIVE LOGITS
    筵
    0.56
     cutlery
    0.54
     ghế
    0.49
     запя
    0.48
     vinaig
    0.48
     Elderly
    0.48
     Surgeons
    0.47
     Hospitals
    0.47
     Commandant
    0.46
     Specifies
    0.46
    Activations Density 0.000%

    No Known Activations