© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40710
    Prev
    Next
    INDEX
    Explanations

    `// Copyright`

    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
    马上
    -1.63
    ſſel
    -1.59
    않
    -1.57
    }
    -1.54
    ர
    -1.50
    ]
    -1.49
     το
    -1.49
     },
    -1.45
     mangled
    -1.44
     apparaissent
    -1.42
    POSITIVE LOGITS
    焢
    1.83
    ekyll
    1.66
     entsprechenden
    1.65
    いただいた
    1.62
     alleviate
    1.62
     godk
    1.62
     burgeoning
    1.59
    سة
    1.58
     причиной
    1.58
    同じ
    1.56
    Activations Density 0.018%

    No Known Activations