© 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. 148317
    Prev
    Next
    INDEX
    Explanations

    company send, cough produces, price is

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

    explanation of ideas

    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
    กับ
    0.53
    µ
    0.52
    Neigh
    0.51
    Pay
    0.49
     עם
    0.49
    ในสนาม
    0.49
     ਦ
    0.48
    lib
    0.47
    lab
    0.46
    ấn
    0.46
    POSITIVE LOGITS
     gerecht
    0.47
     fara
    0.47
    த்தனர்
    0.46
     noten
    0.46
     gastric
    0.45
    ５
    0.45
     Wir
    0.44
     hepatocellular
    0.44
     pote
    0.44
     paradox
    0.43
    Activations Density 0.000%

    No Known Activations