© 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. 44824
    Prev
    Next
    INDEX
    Explanations

    physical harm or injury

    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
     yetu
    -1.75
     this
    -1.44
     オレンジ
    -1.43
     invester
    -1.42
     piac
    -1.38
     autorisation
    -1.32
     tilla
    -1.32
    ぞれ
    -1.32
     barnet
    -1.32
    czej
    -1.30
    POSITIVE LOGITS
     and
    1.55
    Both
    1.49
     Fähig
    1.48
    ↵
    1.48
    cookieParser
    1.36
     numerosas
    1.34
    させていただきました
    1.30
     jeweiligen
    1.28
    Using
    1.27
     previously
    1.27
    Activations Density 0.046%

    No Known Activations