© 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. 70204
    Prev
    Next
    INDEX
    Explanations

    match sanctioned, many emotions

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

    can lead to consequences

    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
     канторы
    0.53
     لين
    0.46
     clippings
    0.44
     рэгістра
    0.44
    িত্তিক
    0.43
     стаўкі
    0.42
     நாடு
    0.42
    疤
    0.42
    韧
    0.42
    ୧
    0.41
    POSITIVE LOGITS
     naval
    0.49
     gay
    0.48
     Drog
    0.48
     EURO
    0.47
     SOD
    0.47
     cambiado
    0.47
     Habsburg
    0.46
     civilization
    0.46
     adoles
    0.46
     Judas
    0.46
    Activations Density 0.002%

    No Known Activations