© 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. 104856
    Prev
    Next
    INDEX
    Explanations

    reaction, scripture, formatting, time, atom, desktop, mvc

    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
    ).
    -2.75
    }
    -2.58
    -2.47
     impeccable
    -2.39
     pentru
    -2.36
    。《
    -2.27
     Begleitung
    -2.27
    ]
    -2.23
    .
    -2.23
     FOR
    -2.22
    POSITIVE LOGITS
    ܃
    2.75
    卝
    2.64
    栊
    2.61
     excellente
    2.53
    苤
    2.50
    蹰
    2.44
    鉿
    2.44
     fabriqué
    2.44
    鮰
    2.44
    〮
    2.33
    Activations Density 0.004%

    No Known Activations