© 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. 114687
    Prev
    Next
    INDEX
    Explanations

    to avoid or help

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

    history, empires, divisive concepts

    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
    ન
    0.55
     grados
    0.52
     nuestro
    0.52
     orientado
    0.50
    漃
    0.49
     regreso
    0.48
     propio
    0.48
    ச
    0.48
     apenas
    0.48
     sencillo
    0.47
    POSITIVE LOGITS
    Dimethyl
    0.45
    cephal
    0.43
    inig
    0.42
     مق
    0.42
    rror
    0.41
     vampire
    0.41
     Examination
    0.41
     uptick
    0.41
     张
    0.40
    2
    0.40
    Activations Density 0.000%

    No Known Activations