© 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. 123916
    Prev
    Next
    INDEX
    Explanations

    remanded; VHS tapes; Riyadh

    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
     It
    -2.47
    噥
    -2.08
     steigen
    -2.06
     If
    -2.02
     Unterschiede
    -1.91
     handels
    -1.90
     Không
    -1.89
    𐌸
    -1.88
     knapp
    -1.85
    やや
    -1.84
    POSITIVE LOGITS
    which
    2.55
    er
    2.31
    ments
    2.23
    quelize
    2.20
    ….
    2.19
    ment
    2.19
    self
    2.17
    ysteine
    2.00
    erer
    1.99
    狁
    1.99
    Activations Density 0.002%

    No Known Activations