© 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. 104396
    Prev
    Next
    INDEX
    Explanations

    quantifying or qualifying subsequent words

    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
    了自己的
    -1.20
    臵
    -1.11
    uksi
    -1.09
    aino
    -1.09
     espírito
    -1.09
     vaše
    -1.09
    gjenge
    -1.06
    ၃
    -1.06
    界的
    -1.06
    чных
    -1.06
    POSITIVE LOGITS
    diğini
    1.42
    diğinde
    1.38
    とある
    1.30
    Dade
    1.23
    ordnet
    1.20
    |'.'
    1.19
    logischen
    1.18
    °
    1.18
    yaratan
    1.14
    owan
    1.13
    Activations Density 0.065%

    No Known Activations