© 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. 31-GEMMASCOPE-2-RES-262K
    7. 2098
    Prev
    Next
    INDEX
    Explanations

    fabric materials

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

    materials and components

    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_31_width_262k_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
    
    0.52
    দায়
    0.51
     overfitting
    0.51
    ക്കള്‍
    0.49
     actinides
    0.49
     রোগের
    0.47
    痙
    0.46
     请求
    0.46
    ския
    0.45
     délais
    0.45
    POSITIVE LOGITS
     Brazilian
    0.57
    teile
    0.54
    ter
    0.53
     mistura
    0.53
     recycled
    0.52
     components
    0.51
    cell
    0.51
    fiber
    0.51
    bit
    0.50
     Japanese
    0.50
    Activations Density 0.070%

    No Known Activations