© 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. 44287
    Prev
    Next
    INDEX
    Explanations

    Chinese names and items

    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
    𝑔
    -1.70
    🤐
    -1.68
    ⽀
    -1.61
     protestas
    -1.59
    轢
    -1.59
    🤨
    -1.55
    😣
    -1.55
    😶
    -1.54
     gedurende
    -1.53
    😤
    -1.52
    POSITIVE LOGITS
     like
    1.91
    1
    1.76
    Because
    1.61
    5
    1.60
     their
    1.56
     .
    1.55
    4
    1.52
     similar
    1.47
    ]
    1.45
    ↵
    1.45
    Activations Density 0.048%

    No Known Activations