© 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. 22-GEMMASCOPE-RES-131K
    7. 11178
    Prev
    Next
    INDEX
    Explanations

    questions starting with does

    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_22/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
     recibo
    -1.15
     traslado
    -1.15
     extraordinario
    -1.10
     logro
    -1.09
     thánh
    -1.08
     owns
    -1.04
     penetrates
    -1.03
     intertw
    -1.02
     aligns
    -1.01
     desnuda
    -1.01
    POSITIVE LOGITS
    </strong>
    2.88
    </b>
    2.53
    </u>
    2.44
    </em>
    2.25
    </i>
    2.09
    </code>
    1.59
    ’
    1.22
     augustus
    1.20
     امریک
    1.18
    -
    1.16
    Activations Density 0.155%

    No Known Activations