© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35619
    Prev
    Next
    INDEX
    Explanations

    pelvicall antiL (reddeningpowerlabels

    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
    >−</
    -1.13
    rospy
    -0.99
    ༌
    -0.88
    ј
    -0.88
    trze
    -0.86
     astonishing
    -0.85
     puoi
    -0.84
     Honourable
    -0.82
     wyposaż
    -0.82
     ベルト
    -0.82
    POSITIVE LOGITS
    ὅ
    0.88
    obatan
    0.84
     ešte
    0.84
     канал
    0.83
     for
    0.82
    houding
    0.81
    angka
    0.80
     Although
    0.76
     ELEVATION
    0.75
     フルーツ
    0.75
    Activations Density 0.125%

    No Known Activations