© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128967
    Prev
    Next
    INDEX
    Explanations

    variable names starting with b

    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
    sich
    -1.54
     paisajes
    -1.48
     télévision
    -1.48
     karier
    -1.48
    nagy
    -1.45
     клей
    -1.39
     सबसे
    -1.38
     colaboradores
    -1.38
    produkte
    -1.38
    wieder
    -1.38
    POSITIVE LOGITS
    </i>
    1.63
    riger
    1.58
    Whether
    1.56
    能否
    1.48
     необходимости
    1.45
     數
    1.44
     whether
    1.39
     cette
    1.38
    能不能
    1.36
    ;
    1.34
    Activations Density 0.007%

    No Known Activations