© 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. 12036
    Prev
    Next
    INDEX
    Explanations

    positive qualities and 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
    隄
    -1.30
    ּוֹ
    -1.25
    菝
    -1.24
     Дет
    -1.23
    了许多
    -1.22
    皝
    -1.21
    Literatuur
    -1.21
     rompi
    -1.20
     neler
    -1.20
    狳
    -1.19
    POSITIVE LOGITS
     your
    1.67
    Also
    1.29
     It
    1.22
    Another
    1.22
     and
    1.20
     at
    1.16
     just
    1.16
    Other
    1.13
     first
    1.13
    For
    1.13
    Activations Density 0.032%

    No Known Activations