© 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. 95458
    Prev
    Next
    INDEX
    Explanations

    material definition or description

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

    material science

    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
     Sentencing
    0.51
     acho
    0.50
     parochial
    0.46
     triste
    0.44
     admittedly
    0.44
     sadly
    0.43
     basados
    0.43
    慚
    0.43
     Highway
    0.42
     palindrome
    0.42
    POSITIVE LOGITS
     matériau
    0.53
     материала
    0.49
     ಅವರು
    0.49
     materi
    0.48
     viscoelastic
    0.47
    bés
    0.46
    ictwa
    0.46
    norod
    0.46
     anyag
    0.46
    工艺
    0.45
    Activations Density 0.001%

    No Known Activations