© 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. 20437
    Prev
    Next
    INDEX
    Explanations

    command assignment

    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
     when
    -1.66
     where
    -1.55
     on
    -1.52
     especially
    -1.52
     celebrating
    -1.52
     other
    -1.48
     specifically
    -1.47
     with
    -1.45
     structured
    -1.43
     isolated
    -1.36
    POSITIVE LOGITS
    Ḱ
    1.76
     to
    1.59
    ፨
    1.47
    XXI
    1.46
    〠
    1.43
     gingen
    1.39
    öner
    1.38
    modb
    1.38
    úmeros
    1.37
    آیا
    1.37
    Activations Density 0.005%

    No Known Activations