© 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. 125825
    Prev
    Next
    INDEX
    Explanations

    round, procedure, similar, diplomatic

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

    medical feeds

    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
    land
    0.53
    ވެ
    0.52
    /
    0.51
    過
    0.50
     distrito
    0.48
    "
    0.48
    ة
    0.48
     rurales
    0.46
     sukar
    0.45
    үй
    0.45
    POSITIVE LOGITS
    точно
    0.52
     साक्षी
    0.49
     실시
    0.48
     філь
    0.46
    _{+}^{
    0.46
    oming
    0.45
     நீரில்
    0.45
    żliw
    0.44
     옳
    0.44
    arrayList
    0.44
    Activations Density 0.001%

    No Known Activations