© 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. 22367
    Prev
    Next
    INDEX
    Explanations

    personal belongings and experiences

    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
    </h3>
    -2.19
     with
    -1.88
     is
    -1.68
    </h1>
    -1.67
     For
    -1.66
     It
    -1.66
     Instead
    -1.66
     décrit
    -1.64
     in
    -1.62
     kompetisi
    -1.60
    POSITIVE LOGITS
    この日
    1.98
    ཎ
    1.75
    Будь
    1.75
    元々
    1.70
     detalj
    1.67
    ,--
    1.65
    几个人
    1.65
    お店の
    1.64
    ,’’
    1.64
     belief
    1.63
    Activations Density 0.012%

    No Known Activations