© 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. 73277
    Prev
    Next
    INDEX
    Explanations

    romantic love and its contexts

    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
    猡
    -2.42
    '
    -2.42
    layed
    -2.41
     slike
    -2.34
     vei
    -2.25
    其妙
    -2.22
    蚰
    -2.14
    -2.13
    桖
    -2.11
    梘
    -2.08
    POSITIVE LOGITS
     که
    2.81
    的山
    2.42
    或
    2.36
     magnétique
    2.28
     یا
    2.28
     piş
    2.25
     define
    2.16
     daring
    2.14
     soggy
    2.13
     wayward
    2.13
    Activations Density 0.017%

    No Known Activations