© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 44096
    Prev
    Next
    INDEX
    Explanations

    vector addition and sum

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     interés
    0.51
    CUR
    0.50
     diminta
    0.50
     хоче
    0.49
    <unused369>
    0.49
    ligo
    0.47
     ønsker
    0.47
    asking
    0.47
    kamer
    0.47
    ουμε
    0.46
    POSITIVE LOGITS
     vectors
    0.65
     географи
    0.61
     geographic
    0.59
     Vectors
    0.57
     geograf
    0.57
     भौगोलिक
    0.56
     geographically
    0.55
     vector
    0.54
    키
    0.54
    Vectors
    0.54
    Activations Density 0.012%

    No Known Activations