© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 85106
    Prev
    Next
    INDEX
    Explanations

    standing orders or committees

    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
    |}{}
    -1.51
     khỏ
    -1.48
     In
    -1.48
    ctuaries
    -1.47
     Jazeera
    -1.45
     مدیریت
    -1.44
    alete
    -1.43
    ittens
    -1.41
    襪
    -1.40
     contient
    -1.38
    POSITIVE LOGITS
    ”:
    2.06
    ”).
    1.95
    !”
    1.90
    ).”
    1.84
    ?”
    1.80
    ”;
    1.80
    </h6>
    1.74
     女の子
    1.72
    </sup>
    1.66
    ”),
    1.63
    Activations Density 0.010%

    No Known Activations