© 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. 66192
    Prev
    Next
    INDEX
    Explanations

    numbers separated by commas

    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
    </h5>
    -1.37
    </h6>
    -1.30
    accompanied
    -1.26
    子ども
    -1.23
     "..\..\
    -1.20
    　「
    -1.20
    </td>
    -1.19
     degust
    -1.17
    ТО
    -1.16
    ТЕ
    -1.15
    POSITIVE LOGITS
    Spesifikasi
    1.16
    <bos>
    1.15
    leys
    1.14
    Karakteristik
    1.12
    ⦑
    1.11
    Cuidado
    1.10
    If
    1.09
     koska
    1.08
    iseaux
    1.08
    веден
    1.08
    Activations Density 0.090%

    No Known Activations