© 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. 47866
    Prev
    Next
    INDEX
    Explanations

    development, music, organisation, gifts

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

    locations and descriptions

    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
     rectification
    0.41
     chrét
    0.40
     продуктов
    0.39
     purchasing
    0.39
    ુર
    0.39
    鉄道
    0.38
    勅
    0.38
    엌
    0.38
    偉
    0.38
     postwar
    0.38
    POSITIVE LOGITS
    apparently
    0.43
     aparentemente
    0.43
     taco
    0.42
     عین
    0.39
     మొక్క
    0.39
    itivo
    0.38
    ativamente
    0.38
    อย่าง
    0.38
    counted
    0.37
    ຢ່າງ
    0.37
    Activations Density 0.000%

    No Known Activations