© 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. 128332
    Prev
    Next
    INDEX
    Explanations

    words involving rev

    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
    ↵↵
    -2.75
     innych
    -2.72
     інших
    -2.70
     a
    -2.59
    迨
    -2.48
    ”.
    -2.41
     speziellen
    -2.41
     assuring
    -2.30
    啬
    -2.28
     refrain
    -2.25
    POSITIVE LOGITS
     aussit
    3.16
     écl
    2.73
    ༵
    2.61
    If
    2.52
    想
    2.52
    𖥦
    2.48
    廛
    2.42
    屺
    2.42
    ཫ
    2.41
     dage
    2.34
    Activations Density 0.004%

    No Known Activations