© 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. 128128
    Prev
    Next
    INDEX
    Explanations

    Instagram, embodiments, Crohn's, Royal Bank

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

    quantities mentioning place or length

    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
    rategy
    0.48
     중심
    0.47
    졍
    0.47
     జ్ఞాప
    0.45
    }}}
    0.45
    ěž
    0.45
    üng
    0.45
     소비
    0.45
     впечат
    0.44
    Olivier
    0.44
    POSITIVE LOGITS
     {
    0.67
     calle
    0.50
    ならない
    0.48
     kios
    0.46
    []{
    0.45
    設備
    0.45
    ;
    0.44
    انے
    0.43
     enige
    0.43
     wol
    0.43
    Activations Density 0.001%

    No Known Activations