© 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. 11741
    Prev
    Next
    INDEX
    Explanations

    company holdings

    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
    t
    -2.56
    焢
    -2.20
    on
    -2.16
    r
    -2.11
    when
    -2.11
    }
    -2.11
     內
    -2.05
    地區
    -2.03
    u
    -2.03
    具有
    -2.00
    POSITIVE LOGITS
    沕
    2.95
     of
    2.52
    </h2>
    2.45
    </em>
    2.44
    𐄁
    2.36
     encontrados
    2.34
    ”)
    2.31
    replyreport
    2.30
    ࿊
    2.25
    </sup>
    2.19
    Activations Density 0.004%

    No Known Activations