© 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. 192174
    Prev
    Next
    INDEX
    Explanations

    CNG fueling

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

    quad jump

    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
     שת
    0.50
    úng
    0.48
     आपका
    0.48
     კ
    0.47
     González
    0.47
     εκεί
    0.46
     للت
    0.46
     Ramos
    0.45
    ؍
    0.45
     لح
    0.44
    POSITIVE LOGITS
    REC
    0.48
    影视
    0.46
    引进
    0.46
    ureate
    0.44
    Overflow
    0.44
    民间
    0.43
    enture
    0.42
    Avengers
    0.42
    Adventure
    0.42
    ertid
    0.42
    Activations Density 0.005%

    No Known Activations