© 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. 87620
    Prev
    Next
    INDEX
    Explanations

    others acting on your behalf

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

    normal or common occurrences

    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
    નાર
    0.50
    䨘
    0.43
     további
    0.43
    anego
    0.42
    Weitere
    0.42
    zonej
    0.41
    㣱
    0.41
    feitura
    0.41
     Instrumentation
    0.40
    ماية
    0.40
    POSITIVE LOGITS
    1
    0.59
     {
    0.51
    カラ
    0.45
    ⌊
    0.43
     $
    0.43
    ディア
    0.43
     असू
    0.43
     asymptotics
    0.42
     bumpy
    0.42
     since
    0.42
    Activations Density 0.000%

    No Known Activations