© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 65731
    Prev
    Next
    INDEX
    Explanations

    direction or symbol followed by comma

    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
    也要
    -1.16
     también
    -1.04
    FILTER
    -1.03
    Кроме
    -1.02
    recycle
    -1.00
     already
    -0.97
    　＊
    -0.96
     myös
    -0.95
     Piedra
    -0.94
     hemen
    -0.93
    POSITIVE LOGITS
     is
    1.43
    }
    1.41
    ⁛
    1.23
    }
    1.19
    setFile
    1.17
    匱
    1.16
     cinquante
    1.16
     UIFont
    1.15
    onyms
    1.14
    yPos
    1.11
    Activations Density 0.280%

    No Known Activations