© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10001
    Prev
    Next
    INDEX
    Explanations

    concrete and brick wall

    np_acts-logits-general · gemini-2.5-flash-lite

    concrete and cement materials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     চলচ্
    0.47
    钽
    0.43
    FileChooser
    0.43
     răz
    0.42
    启发
    0.42
     चैल
    0.42
    xv
    0.41
    avelength
    0.41
    DeviceCompliance
    0.40
    辕
    0.40
    POSITIVE LOGITS
     concrete
    1.91
     Concrete
    1.89
     бетон
    1.89
    Concrete
    1.84
    concrete
    1.83
    混凝土
    1.79
     cement
    1.75
     beton
    1.71
     béton
    1.71
     Cement
    1.65
    Activations Density 0.582%

    No Known Activations