© 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. 10289
    Prev
    Next
    INDEX
    Explanations

    counting items quantity

    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
    ，
    -2.20
    、
    -1.94
    >
    -1.84
    ،
    -1.81
    你
    -1.78
    9
    -1.73
     -
    -1.67
    3
    -1.67
    :'
    -1.65
    大
    -1.63
    POSITIVE LOGITS
     of
    2.02
    以外にも
    1.61
    kệ
    1.55
    瓛
    1.55
     distingu
    1.55
    几分
    1.52
    スポンサーリンク
    1.52
     have
    1.51
    のおかげ
    1.49
     nabízí
    1.49
    Activations Density 0.065%

    No Known Activations