© 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. 53809
    Prev
    Next
    INDEX
    Explanations

    text examples

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

    comparisons of properties

    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
     assisted
    0.43
     assisting
    0.42
     reduced
    0.41
    消除
    0.41
    胺
    0.41
    ocal
    0.40
    bagi
    0.39
    нинг
    0.39
    ̀
    0.39
    нг
    0.39
    POSITIVE LOGITS
     teks
    0.55
     tendances
    0.55
     coisas
    0.53
     texte
    0.53
     بعض
    0.52
     textos
    0.52
     exemplos
    0.51
     textes
    0.50
     tendencias
    0.49
     ejemplos
    0.49
    Activations Density 0.000%

    No Known Activations