© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44120
    Prev
    Next
    INDEX
    Explanations

    states of mind or being

    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
     Japão
    -1.58
    、『
    -1.51
    lında
    -1.40
     povo
    -1.34
    かというと
    -1.34
     following
    -1.32
    鹚
    -1.26
     filósofo
    -1.23
     because
    -1.23
     when
    -1.23
    POSITIVE LOGITS
    ícias
    1.55
     [
    1.35
    ]}$
    1.34
    ları
    1.34
    acterium
    1.31
     dessutom
    1.27
    orsal
    1.22
    不明白
    1.22
    </sup>
    1.21
     anvä
    1.21
    Activations Density 0.014%

    No Known Activations