© 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. 104443
    Prev
    Next
    INDEX
    Explanations

    words starting with agg

    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
    ).
    -2.64
    畯
    -2.55
    ,’”
    -2.31
    衚
    -2.30
    </h3>
    -2.30
    」，
    -2.27
    焄
    -2.25
    隄
    -2.23
    逦
    -2.20
    廕
    -2.20
    POSITIVE LOGITS
    笮
    2.63
    s
    2.61
    ?"
    2.53
    其妙
    2.53
     に関する
    2.39
    的话
    2.38
    氽
    2.38
    ︕
    2.36
    𓍊
    2.30
    5
    2.28
    Activations Density 0.002%

    No Known Activations