© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99758
    Prev
    Next
    INDEX
    Explanations

    pom.xml files

    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
    瞜
    -2.84
    峩
    -2.63
    𖥦
    -2.59
    〤
    -2.53
    嗞
    -2.52
     voor
    -2.52
    伈
    -2.45
    }$.
    -2.44
     они
    -2.39
     ソックス
    -2.39
    POSITIVE LOGITS
    1
    2.89
    ジュース
    2.52
    –
    2.25
    </strong>
    2.25
    随后
    2.25
     Owing
    2.23
     bestanden
    2.20
    漚
    2.16
    \
    2.13
    早已
    2.08
    Activations Density 0.006%

    No Known Activations