© 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. 10-GEMMASCOPE-RES-131K
    7. 47498
    Prev
    Next
    INDEX
    Explanations

    moving or relocation

    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
    )」
    -2.52
    It
    -2.36
    In
    -2.31
    C
    -2.28
     einfache
    -2.28
    And
    -2.27
     heutige
    -2.25
    o
    -2.25
    On
    -2.19
     ganze
    -2.17
    POSITIVE LOGITS
    鸶
    2.94
     ‘
    2.55
     parachoque
    2.48
    Ⲉ
    2.45
    更何况
    2.41
    fashioned
    2.30
    を活用
    2.28
    ności
    2.27
    栳
    2.25
    但却
    2.23
    Activations Density 0.003%

    No Known Activations