© 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. 130816
    Prev
    Next
    INDEX
    Explanations

    even so, gradually

    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
    </td>
    -1.97
    </b>
    -1.93
    鷙
    -1.88
    мії
    -1.82
    甞
    -1.80
    </h5>
    -1.77
     Tires
    -1.68
    ⸨
    -1.67
    鐒
    -1.64
     Wires
    -1.61
    POSITIVE LOGITS
    The
    2.02
     []:
    1.84
    卺
    1.82
     they
    1.77
     一
    1.75
    起的
    1.74
     RequestMethod
    1.70
     Tamaño
    1.70
    就像是
    1.67
     Dimensiones
    1.67
    Activations Density 0.001%

    No Known Activations