© 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. 104447
    Prev
    Next
    INDEX
    Explanations

    states and legal entities

    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
     today
    -1.45
     last
    -1.43
    </b>
    -1.42
     masih
    -1.35
     başlay
    -1.30
    dä
    -1.25
    ны
    -1.24
    riet
    -1.24
     to
    -1.23
     tonight
    -1.23
    POSITIVE LOGITS
     extranjera
    1.25
     equipaje
    1.19
    even
    1.19
    円で
    1.17
    他們
    1.17
    O
    1.16
    in
    1.16
    werben
    1.11
     both
    1.09
    Both
    1.09
    Activations Density 0.098%

    No Known Activations