© 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. 22-GEMMASCOPE-RES-131K
    7. 33256
    Prev
    Next
    INDEX
    Explanations

    comparison 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_22/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
    を
    -1.74
     of
    -1.66
    も
    -1.27
    が
    -1.25
    齟
    -1.20
    〜。
    -1.17
    や
    -1.13
    などの
    -1.13
     nonché
    -1.12
     그는
    -1.07
    POSITIVE LOGITS
    SHIRE
    1.03
    の人に
    1.02
     deixando
    1.01
     mélang
    0.98
    eronau
    0.95
    ジュアル
    0.94
    ξεις
    0.94
    趿
    0.93
     anoche
    0.93
    先週
    0.93
    Activations Density 0.001%

    No Known Activations