© 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. 244213
    Prev
    Next
    INDEX
    Explanations

    change without oversight

    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
     అతను
    0.49
     తెలు
    0.47
    䣷
    0.46
     девочки
    0.46
     دیگه
    0.46
    CYCL
    0.44
     রাজাকার
    0.44
    Estamos
    0.44
    ך
    0.43
     ویک
    0.43
    POSITIVE LOGITS
     disponer
    0.54
     emphasises
    0.46
     gewisse
    0.45
     diversas
    0.44
     anu
    0.44
     stets
    0.43
     situations
    0.43
     diversos
    0.43
     emphasise
    0.43
     contrad
    0.42
    Activations Density 0.001%

    No Known Activations