© 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. 103753
    Prev
    Next
    INDEX
    Explanations

    the word evidence

    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
    ."
    -2.69
    ”
    -2.67
    },
    -2.64
    D
    -2.61
    ]
    -2.53
    ти
    -2.52
    一些
    -2.48
    也许
    -2.48
     '
    -2.42
    های
    -2.42
    POSITIVE LOGITS
    鹮
    2.73
    <bos>
    2.73
    柠
    2.72
    ţin
    2.70
     prohibido
    2.67
     they
    2.64
     him
    2.63
    нутрен
    2.61
    
    2.59
    
    2.58
    Activations Density 0.013%

    No Known Activations