© 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. 38899
    Prev
    Next
    INDEX
    Explanations

    people's names

    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
     many
    -1.43
     our
    -1.42
     '
    -1.37
     viele
    -1.28
    mbda
    -1.28
     any
    -1.27
     with
    -1.27
     nossas
    -1.27
     /
    -1.23
    嗌
    -1.21
    POSITIVE LOGITS
     réparer
    1.21
    ⃤
    1.19
    ⚣
    1.18
     emporter
    1.11
     distante
    1.10
    très
    1.09
     QUIZ
    1.08
    잘
    1.07
    ţiei
    1.05
     riu
    1.05
    Activations Density 0.103%

    No Known Activations