© 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. 130706
    Prev
    Next
    INDEX
    Explanations

    keeping and maintaining states

    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
    賔
    -1.39
    Institu
    -1.27
    Kritik
    -1.22
    KommentareTeilen
    -1.22
     about
    -1.21
     opět
    -1.21
     debió
    -1.20
    Neden
    -1.20
    Autre
    -1.20
    觊
    -1.20
    POSITIVE LOGITS
    保持
    1.56
    ’
    1.48
    maintain
    1.38
    Keep
    1.37
    的一
    1.36
    keep
    1.35
    ();
    1.34
     keep
    1.34
    ”:
    1.30
    and
    1.30
    Activations Density 0.394%

    No Known Activations