© 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. 127916
    Prev
    Next
    INDEX
    Explanations

    lost in translation or drowned

    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
    </i>
    -1.71
     */
    -1.60
     sabias
    -1.46
     desnuda
    -1.45
     garantiert
    -1.42
     where
    -1.41
     був
    -1.41
     was
    -1.40
     %).
    -1.38
    colori
    -1.38
    POSITIVE LOGITS
    waite
    1.43
    Также
    1.41
     trivi
    1.37
    日本では
    1.29
    iblichen
    1.26
     slander
    1.19
    伝統
    1.17
     bohemian
    1.16
    Jumlah
    1.16
    诰
    1.16
    Activations Density 0.031%

    No Known Activations