© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 123809
    Prev
    Next
    INDEX
    Explanations

    television followed by series or films

    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
     некоторые
    -1.46
    s
    -1.20
     […]
    -1.16
     importantly
    -1.14
    tte
    -1.14
    they
    -1.12
     другие
    -1.12
    𝒛
    -1.11
     キング
    -1.10
     voce
    -1.09
    POSITIVE LOGITS
     to
    1.57
     &
    1.50
    UCTION
    1.46
    cellent
    1.43
    Đây
    1.41
    Приятного
    1.37
    Với
    1.36
    真的
    1.36
     možno
    1.35
    Väl
    1.34
    Activations Density 0.038%

    No Known Activations