© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8270
    Prev
    Next
    INDEX
    Explanations

    action and actions

    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
    latter
    -1.32
    缭
    -1.28
    ‚¬
    -1.27
     которы
    -1.26
    adds
    -1.25
     nėra
    -1.24
    ه‌ی
    -1.23
    PENUTUP
    -1.23
     đó
    -1.20
     nho
    -1.20
    POSITIVE LOGITS
     to
    2.03
     diversa
    1.32
     have
    1.30
     measures
    1.29
    ㈠
    1.27
    ISTRATION
    1.27
     continues
    1.23
     again
    1.21
     różne
    1.20
    に関して
    1.20
    Activations Density 0.033%

    No Known Activations