© 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. 68763
    Prev
    Next
    INDEX
    Explanations

    represented by

    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
     to
    -1.24
    ſſen
    -1.06
    というもの
    -1.05
    珰
    -1.05
     nötig
    -1.03
    fordshire
    -1.02
    俬
    -1.00
    ఝ
    -1.00
     članak
    -0.98
     ſte
    -0.98
    POSITIVE LOGITS
     in
    2.61
     by
    2.41
     with
    1.83
     within
    1.27
    UNIVERSIDAD
    1.23
    miendo
    1.11
     kehadiran
    1.10
    鐧
    1.10
     követ
    1.09
     државе
    1.08
    Activations Density 0.070%

    No Known Activations