© 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. 69116
    Prev
    Next
    INDEX
    Explanations

    personality traits and types

    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
     to
    -1.43
     itself
    -1.41
    </i>
    -1.38
     ACCIDENT
    -1.32
     is
    -1.28
     behandelt
    -1.25
    糁
    -1.24
     PERSPECT
    -1.23
     the
    -1.22
     its
    -1.20
    POSITIVE LOGITS
     邊
    1.41
    rån
    1.33
     vervolgens
    1.29
    錚
    1.28
     there
    1.23
    circled
    1.22
    城主
    1.22
    蜆
    1.20
     újra
    1.20
    戦う
    1.20
    Activations Density 0.054%

    No Known Activations