© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 7918
    Prev
    Next
    INDEX
    Explanations

    technical network terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    2
    -3.20
    埽
    -2.86
    気付
    -2.55
     chirurg
    -2.50
     erhi
    -2.47
    にゃ
    -2.30
    お待ちしております
    -2.30
    僦
    -2.30
     Examining
    -2.28
    を始め
    -2.27
    POSITIVE LOGITS
    蔔
    2.98
    ....
    2.61
     müssen
    2.58
    郿
    2.53
     esteemed
    2.48
     lanzó
    2.48
    で
    2.48
    :
    2.47
    跋
    2.47
    一定的
    2.44
    Activations Density 0.026%

    No Known Activations