© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 119772
    Prev
    Next
    INDEX
    Explanations

    actions and their objects

    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
     like
    -1.39
    ₁)
    -1.16
    .}(
    -1.16
    ]),
    
    -1.13
     so
    -1.09
    '
    -1.09
    *}[
    -1.07
    pright
    -1.06
    ñar
    -1.05
    })*/
    -1.05
    POSITIVE LOGITS
     Ayuda
    1.19
     Aucune
    1.12
    guigu
    1.11
     Introducción
    1.10
     Hinweis
    1.10
     Artículo
    1.09
     Trouvez
    1.08
    𝔗
    1.08
     アウトドア
    1.07
     each
    1.06
    Activations Density 0.204%

    No Known Activations