© 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. 12084
    Prev
    Next
    INDEX
    Explanations

    interplay of or between

    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
    其妙
    -2.91
    ]
    -2.72
    AN
    -2.67
    佧
    -2.28
    </i>
    -2.22
     envisioned
    -2.22
     envisaged
    -2.20
    ON
    -2.19
    䉴
    -2.14
    ௜
    -2.13
    POSITIVE LOGITS
    ...(
    3.05
    e
    3.00
    翃
    2.52
     This
    2.52
    嚶
    2.48
    the
    2.41
    都有
    2.38
     and
    2.33
    off
    2.25
    ...
    2.25
    Activations Density 0.007%

    No Known Activations