© 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. 113007
    Prev
    Next
    INDEX
    Explanations

    simulator contexts

    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
    栳
    -2.64
    𝐒
    -2.61
    ТОВ
    -2.44
     сист
    -2.36
     lament
    -2.27
    みてください
    -2.25
    Ş
    -2.19
    втра
    -2.19
    倥
    -2.17
     frågan
    -2.16
    POSITIVE LOGITS
    茀
    2.55
    .
    2.34
     manter
    2.34
    瑒
    2.27
    </h3>
    2.25
    にほんブログ村
    2.23
     “
    2.23
    ;”
    2.22
    髏
    2.19
    <bos>
    2.17
    Activations Density 0.003%

    No Known Activations