© 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. 9
    Prev
    Next
    INDEX
    Explanations

    hit or press an action

    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
    )
    -1.51
    when
    -1.47
    because
    -1.44
    /"
    -1.43
    </h3>
    -1.41
    5
    -1.39
    不仅
    -1.36
    Usted
    -1.30
    Alguien
    -1.30
     esos
    -1.29
    POSITIVE LOGITS
     to
    1.52
    ︲
    1.48
    logique
    1.34
     ardından
    1.34
    РЯ
    1.33
     poème
    1.30
    ЦА
    1.29
    %%%%%%%%%%
    1.29
     eliminare
    1.29
     Alguns
    1.27
    Activations Density 0.030%

    No Known Activations