© 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. 69234
    Prev
    Next
    INDEX
    Explanations

    input attributes: id, value, placeholder

    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
     its
    -1.46
    k
    -1.40
     eget
    -1.36
    　　《
    -1.36
    ématiques
    -1.29
     simbol
    -1.27
    ⌉
    -1.23
     their
    -1.23
    </u>
    -1.20
     ilang
    -1.19
    POSITIVE LOGITS
    конец
    1.46
    ovým
    1.45
    Біографія
    1.36
    ्ञ
    1.36
     Both
    1.34
     Selasa
    1.34
     be
    1.33
    疚
    1.32
     будете
    1.31
    žiai
    1.30
    Activations Density 0.017%

    No Known Activations