© 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. 198123
    Prev
    Next
    INDEX
    Explanations

    weld, soldered, iPhone models

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

    minimizing travel or legal periods

    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
    羧
    0.47
     과학
    0.47
    㽚
    0.46
    ново
    0.46
    ज़ार
    0.46
    鸫
    0.45
     깨
    0.45
    猜测
    0.45
    ૧
    0.44
    讴
    0.44
    POSITIVE LOGITS
     between
    0.49
     or
    0.49
    num
    0.46
    ون
    0.46
     spouses
    0.46
     بين
    0.46
    days
    0.44
    between
    0.44
     povinn
    0.44
     restaurant
    0.44
    Activations Density 0.000%

    No Known Activations