© 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. 138539
    Prev
    Next
    INDEX
    Explanations

    artworknighthoursyourMillersorrow

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

    Boosts earnings, sleep apnea, blogging, server access

    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
    ᇁ
    0.49
    த்தனர்
    0.49
     поверну
    0.48
    BLE
    0.46
    resulting
    0.46
    むしろ
    0.46
    穀
    0.46
     җиңү
    0.45
    欳
    0.45
    ütfen
    0.45
    POSITIVE LOGITS
     Bur
    0.55
     OSS
    0.53
     Public
    0.52
    ↵↵
    0.52
     Sant
    0.49
     carin
    0.47
     Toscana
    0.47
     Stock
    0.46
     Rom
    0.46
     Rams
    0.46
    Activations Density 0.000%

    No Known Activations