© 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. 120046
    Prev
    Next
    INDEX
    Explanations

    tuning or tuned

    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
     Of
    -2.45
     был
    -2.27
     };
    -2.16
     angegebenen
    -2.06
    seamnă
    -2.05
     Then
    -2.03
    ']").
    -2.02
     또는
    -1.99
    breviations
    -1.98
     Allowing
    -1.98
    POSITIVE LOGITS
    o
    2.22
    了两
    2.16
    部分が
    2.09
     малыша
    2.06
    ſſen
    2.06
     engraçadas
    2.05
    ケース
    2.03
    搂
    2.02
    <i>
    1.99
    that
    1.99
    Activations Density 0.010%

    No Known Activations