© 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. 58746
    Prev
    Next
    INDEX
    Explanations

    test of time, surprise, welcome

    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
    >
    -1.50
     giebt
    -1.40
    .>
    -1.40
     setelah
    -1.38
    >
    -1.36
    ᓚ
    -1.35
     cambiamento
    -1.34
     disimpan
    -1.30
     naudoti
    -1.29
    ~.
    -1.28
    POSITIVE LOGITS
     on
    1.61
      
    1.59
     as
    1.54
     поскольку
    1.26
    </b>
    1.26
    разви
    1.18
     sobre
    1.17
     V
    1.16
     १
    1.15
     R
    1.12
    Activations Density 0.118%

    No Known Activations