© 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. 240808
    Prev
    Next
    INDEX
    Explanations

    messages or worried

    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
     claras
    0.57
    ச்சை
    0.49
     bales
    0.46
    énés
    0.45
    线
    0.45
     aviones
    0.44
     cartas
    0.44
     atteggi
    0.44
     puestos
    0.43
    icción
    0.43
    POSITIVE LOGITS
     Оба
    0.48
     마
    0.48
     Архивная
    0.45
     когда
    0.45
     ሁሉ
    0.44
     Grub
    0.44
     माफ
    0.44
    өрд
    0.44
     GL
    0.43
    )‏
    0.43
    Activations Density 0.000%

    No Known Activations