© 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. 34-GEMMASCOPE-RES-131K
    4. 31751
    Prev
    Next
    INDEX
    Explanations

    logical and conditional operators

    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_34/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
    なのだ
    -0.98
     amarillo
    -0.98
    必要がある
    -0.95
     unaweza
    -0.93
     lavet
    -0.93
    ようだ
    -0.92
    Мини
    -0.91
     Concepción
    -0.91
     pudesse
    -0.90
    Remix
    -0.89
    POSITIVE LOGITS
     and
    2.70
     but
    1.67
     or
    1.56
     while
    1.30
     вместе
    1.17
     xor
    1.16
     junto
    1.13
     alongside
    1.12
     &&
    1.07
     if
    1.05
    Activations Density 0.010%

    No Known Activations