© 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. 13947
    Prev
    Next
    INDEX
    Explanations

    URLs with numbers and delimiters

    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
     when
    -1.72
     confirmado
    -1.51
     ."
    -1.47
     detenido
    -1.44
    odore
    -1.41
     condenado
    -1.41
     venganza
    -1.40
     sufrido
    -1.38
     participado
    -1.38
    -1.32
    POSITIVE LOGITS
    ↵
    1.84
     they
    1.69
     наконец
    1.50
    ية
    1.45
    Tengo
    1.43
    Ejemplos
    1.42
     terjadi
    1.39
     ſont
    1.39
     ライン
    1.38
     –
    1.38
    Activations Density 0.003%

    No Known Activations