© 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. 44104
    Prev
    Next
    INDEX
    Explanations

    subjective states and judgments

    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
    aná
    -1.22
    šní
    -1.21
     letzt
    -1.21
     erfü
    -1.20
     politische
    -1.20
     a
    -1.19
    oustics
    -1.18
     erzä
    -1.17
    鹭
    -1.13
     niềm
    -1.13
    POSITIVE LOGITS
    </h1>
    1.28
    enough
    1.13
    graphies
    1.13
     milliards
    1.12
    want
    1.05
    ѡ
    1.05
    的效果
    1.05
    のよう
    1.04
     ragazza
    1.02
     saken
    1.02
    Activations Density 0.088%

    No Known Activations