© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8981
    Prev
    Next
    INDEX
    Explanations

    computer science and related domains

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

    computer vision science fraud

    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_40_width_16k_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
    electronic
    0.49
    цов
    0.47
    电子
    0.46
     Electronic
    0.44
    цова
    0.44
     impresa
    0.44
    ević
    0.44
    訃
    0.44
    Electronic
    0.43
    ナソニック
    0.43
    POSITIVE LOGITS
     PC
    0.59
     pc
    0.57
    ized
    0.53
    isation
    0.47
     emb
    0.47
     PCs
    0.46
     embroidery
    0.46
    PC
    0.45
    ScienceStudent
    0.45
     tomography
    0.44
    Activations Density 0.115%

    No Known Activations